The Colloquium on Digital Transformation is a series of weekly online talks on how artificial intelligence, machine learning, and big data can lead to scientific breakthroughs with large-scale societal benefit.

REGISTER for the Spring Series

Spring 2021 Series

May 13, 2021, 1 pm PT/4 pm ET

Graceful AI: Backward-Compatibility, Positive-Congruent Training, and the Search for Desirable Behavior of Deep Neural Networks

Stefano Soatto, Vice President of Applied Science, Amazon Web Services and Professor of Computer Science, UCLA

As machine learning-based decision systems improve rapidly, we are discovering that it is no longer enough for them to perform well on their own. They should also behave nicely towards their predecessors and peers. More nuanced demands beyond accuracy now drive the learning process, including robustness, explainability, transparency, fairness, and now also compatibility and regression minimization. We call this “Graceful AI,’’ because in 2021, when we replace an old trained classifier with a new one, we should expect a peaceful transfer of decision powers.

Today, a new model can introduce errors that the old model did not make, despite significantly improving average performance. Such “regression” can break post-processing pipelines, or cause the need to reprocess large amounts of data. How can we train machine learning models to not only minimize the average error, but also minimize “regression”? Can we design and train new learning-based models in a manner that is compatible with previous ones, so that it is not necessary to re-process any data?

These problems are prototypical of the nascent field of cross-model compatibility in representation learning. I will describe the first approach to Backward-Compatible Training (BCT), introduced at the last Conference on Computer Vision and Pattern Recognition (CVPR), and an initial solution to the problem of Positive-Congruent Training (PC-Training), a first step towards “regression constrained” learning, to appear at the next CVPR. Along the way, I will also introduce methodological innovations that enable full-network fine-tuning by solving a linear-quadratic optimization. Such Linear-Quadratic Fine-Tuning (LQF, also to appear at the next CVPR) achieves performance equivalent to non-linear fine-tuning, and superior in the low-data regime, while allowing easy incorporation of convex constraints.

Stefano Soatto

Stefano Soatto is Vice President of Applied Science at Amazon Web Services AI, where he oversees research for AI Applications including vision (Custom Labels, Lookout4Vision), speech (Amazon Transcribe), natural language (Amazon Comprehend, Amazon Lex, Amazon Kendra, Amazon Translate), Document Understanding (Amazon Textract), time series analysis (Amazon Forecast, Lookout4Metrics, Lookout4Equipment), personalization (Amazon Personalize) and others in the works. He is also a Professor of Computer Science at UCLA and founding director of the UCLA Vision Lab.

May 20, 2021, 1 pm PT/4 pm ET

Jeff Shamma, Professor, Department of Industrial and Enterprise Systems Engineering, University of Illinois at Urbana-Champaign

Past Talks

May 6, 2021, 1 pm PT/4 pm ET

Bringing Social Distancing to Light: Architectural Interventions for COVID-19 Containment

Stefana Parascho, Assistant Professor of Architecture, Princeton University
Corina Tarnita, Associate Professor of Ecology and Evolutionary Biology, Princeton University

With the spread of COVID-19, social distancing has become an integral part of our everyday lives. Worldwide, efforts are focused on identifying ways to reopen public spaces, restart businesses, and reintroduce physical togetherness. We believe that architecture plays a key role in the return to a healthy public life by providing a means for controlling distances between people. Making use of computational processing power and data accessibility, we investigate how we can promote healthy and efficient movement through public spaces. Our approach is dynamic, to easily accommodate developing requirements and programmatic changes within these spaces.


Stefana Parascho, Assistant Professor of Architecture at Princeton University, is an architect with teaching and research in the field of computational design and robotic fabrication. Prior to joining Princeton University, she completed her doctorate at ETH Zurich and her architectural studies at the University of Stuttgart. Her research interest lies at the intersection of design, structure, and fabrication, with a focus on fabrication-informed design. She explores computational design methods and their potential role for architectural construction, ranging from agent-based models to mathematical optimization. Her goal is to strengthen the connection between design, structure, and fabrication and the interdisciplinary nature of architectural design through the development of accessible computational design tools.

Tarnita Hi Res

Corina Tarnita is an Associate Professor in Ecology and Evolutionary Biology and the Director of the Program in Environmental Studies at Princeton University. Previously, she was a Junior Fellow at the Harvard Society of Fellows (2010-2012). She obtained her B.A. (2006), M.A. (2008), and PhD (2009) in Mathematics from Harvard University. She is an ESA Early Career Fellow, a Kavli Frontiers of Science Fellow of the National Academy of Sciences, and an Alfred P. Sloan Research Fellow. Her work is centered around the emergence of complex behavior out of simple interactions, across spatial and temporal scales.

April 29, 2021, 1 pm PT/4 pm ET

Understanding Deep Learning through Optimization Bias

Nathan Srebro, Professor, Toyota Technological Institute at Chicago

How and why are we succeeding in training huge non-convex deep networks? How can deep neural networks with billions of parameters generalize well, despite not having enough capacity to overfit any data? What is the true inductive bias of deep learning? And, does it all just boil down to a big fancy kernel machine? In this talk, I will highlight the central role the optimization geometry and optimization dynamics play in determining the inductive bias of deep learning, showing how specific optimization methods can allow generalization even in underdetermined overparameterized models.


Nathan Srebro is interested in statistical and computational aspects of machine learning, and the interaction between them. He has done theoretical work in statistical learning theory and in algorithms, devised novel learning models and optimization techniques, and has worked on applications in computational biology, text analysis, and collaborative filtering. Before coming to TTIC, Srebro was a postdoctoral fellow at the University of Toronto and a visiting scientist at IBM Research.

April 22, 2021, 1 pm PT/4 pm ET

Is Local Information Enough to Predict an Epidemic?

Christian Borgs, Professor of Computer Science, University of California, Berkeley

While simpler models of epidemics assume homogeneous mixing, it is clear that the structure of our social networks is important for the spread of an infection, with degree inhomogeneities and the related notion of super-spreaders being just the obvious reasons. This raises the question of whether knowledge of the local structure of a network is enough to predict the probability and size of an epidemic. More precisely, one might wonder if by having access to randomly sampled nodes in the network and their neighborhoods, we can predict the above quantities. It turns out that, in general, the answer to this question is negative, as the example of isolated, large communities show. However, under a suitable assumption on the global structure of the network, the size and probability of an outbreak can be determined from local graph features. This research is joint work with Yeganeh Alimohammadi and Amin Saberi from Stanford University.

Christian Borgs

Christian Borgs is a professor of Computer Science in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley and a member of the Berkeley Artificial Intelligence Research (BAIR) Lab. He graduated in Physics at the University of Munich and holds a Ph.D. in Mathematical Physics from the University of Munich and the Max-Planck-Institute for Physics. In 1997, he joined Microsoft Research, where he co-founded the Theory Group and served as its manager until 2008, when he co-founded Microsoft Research New England in Cambridge, Massachusetts, until he joined UC Berkeley in 2020. A Fellow of both the American Mathematical Society and the American Association for the Advancement of Science, his current research focuses on responsible AI, from differential privacy to questions of bias in automatic decision making.

April 15, 2021, 1 pm PT/4 pm ET

AI Enabled Deep Mutational Scanning of Interaction between SARS-CoV-2 Spike Protein S and Human ACE2 Receptor

Diwakar Shukla, Assistant Professor, Department of Chemical and Biomolecular Engineering, University of Illinois at Urbana-Champaign

The rapid and escalating spread of SARS-CoV-2 poses an immediate public health emergency. The viral spike protein S binds ACE2 on host cells to initiate molecular events that release the viral genome intracellularly. Soluble ACE2 inhibits entry of both SARS and SARS-2 coronaviruses by acting as a decoy for S binding sites, and is a candidate for therapeutic and prophylactic development. Deep mutational scans is one of the approaches that could provide such a detailed map of protein-protein interactions. However, this technique suffers from several issues such as experimental noise, expensive experimental protocol and lack of techniques that could provide second or higher-order mutation effects. In this talk, we describe an approach that employs a recently developed platform, TLmutation, that could enable rapid investigation of sequence-structure-function relationship of proteins. In particular, we employ a transfer learning approach to generate high-fidelity scans from noisy experimental data and transfer the knowledge from single point mutation data to generate higher-order mutational scans from the single amino-acid substitution data. Using deep mutagenesis, variants of ACE2 will be identified with increased binding to the receptor binding domain of S at a cell surface. We plan to employ the information from the preliminary mutational landscape to generate the high order mutations in ACE2 that could enhance binding to S protein. We also aim to investigate this problem using distributed computing approaches to understand the underlying physics of the spike protein and ACE2 interaction.

Diwakar Shukla

Diwakar Shukla is the Blue Waters Assistant Professor, Department of Chemical and Biomolecular Engineering at the University of Illinois at Urbana-Champaign. His research is focused on understanding the complex biological processes using novel physics-based models and techniques. He received his B.Tech and M.Tech. degrees from the Indian Institute of Technology in Bombay and his MS and PhD degrees from the Massachusetts Institute of Technology. His postdoctoral work was at Stanford University. He has received several awards for his research including the Peterson award from ACS, Innovation in Biotechnology award from AAPS, COMSEF Graduate student award from AIChE, Institute Silver Medal and Manudhane Award from IIT Bombay.

April 8, 2021, 1 pm PT/4 pm ET

Recent Advances in the Analysis of the Implicit Bias of Gradient Descent on Deep Networks

Matus Telgarsky, Assistant Professor of Computer Science, University of Illinois at Urbana-Champaign

In Chicago and elsewhere across the U.S., Latinx and Black communities have experienced disproportionate morbidity and mortality from COVID-19, highlighting drastic health inequities. Testing and vaccination efforts need to be scaled up within communities disproportionately affected by economic vulnerability, housing instability, limited healthcare access, and incarceration. Agent-based models (ABMs) can be used to investigate the complex processes by which social determinants of health influence population-level COVID-19 transmission and mortality, and to conduct computational experiments to evaluate the effects of candidate policies or interventions. Through partnerships between the University of Chicago, Argonne National Laboratory, the Chicago Department of Public Health, and the Illinois COVID-19 Modeling Task Force, we combined multiple data sources to develop a locally informed, realistic, and statistically representative synthetic agent population, with attributes and processes that reflect real-world social and biomedical aspects of transmission. We built a stochastic ABM (CityCOVID) capable of modeling millions of agents representing the behaviors and social interactions, geographic locations, and hourly activities of the population of Chicago and surrounding areas. Transitions between disease states depend on agent attributes and exposure to infected individuals through co-location, placed-based risks, and protective behaviors. The model provides a platform for evaluating how social determinants of health impact COVID-19 transmission, testing, and vaccine uptake and testing optimal approaches to intervention deployment. We discuss implications for public health interventions and policies to address health inequities.


Matus Telgarsky is an Assistant Professor of Computer Science at the University of Illinois at Urbana-Champaign, specializing in deep learning theory. He received a PhD at the University of California, San Diego under Sanjoy Dasgupta. He co-founded the Midwest ML Symposium in 2017 with Po-Ling Loh and organized a Simons Institute summer 2019 program on deep learning with Samy Bengio, Aleskander Madry, and Elchanan Mossel. He received an NSF CAREER Award in 2018.

April 1, 2021, 1 pm PT/4 pm ET

Agent-based Modeling to Understand Social Determinants of Health as Drivers of COVID-19 Epidemics and Test Interventions to Reduce Health Inequities

Anna Hotton, Research Assistant Professor, Department of Medicine, University of Chicago
Jonathan Ozik, Computational Scientist, Argonne National Laboratory

In Chicago and elsewhere across the U.S., Latinx and Black communities have experienced disproportionate morbidity and mortality from COVID-19, highlighting drastic health inequities. Testing and vaccination efforts need to be scaled up within communities disproportionately affected by economic vulnerability, housing instability, limited healthcare access, and incarceration. Agent-based models (ABMs) can be used to investigate the complex processes by which social determinants of health influence population-level COVID-19 transmission and mortality, and to conduct computational experiments to evaluate the effects of candidate policies or interventions. Through partnerships between the University of Chicago, Argonne National Laboratory, the Chicago Department of Public Health, and the Illinois COVID-19 Modeling Task Force, we combined multiple data sources to develop a locally informed, realistic, and statistically representative synthetic agent population, with attributes and processes that reflect real-world social and biomedical aspects of transmission. We built a stochastic ABM (CityCOVID) capable of modeling millions of agents representing the behaviors and social interactions, geographic locations, and hourly activities of the population of Chicago and surrounding areas. Transitions between disease states depend on agent attributes and exposure to infected individuals through co-location, placed-based risks, and protective behaviors. The model provides a platform for evaluating how social determinants of health impact COVID-19 transmission, testing, and vaccine uptake and testing optimal approaches to intervention deployment. We discuss implications for public health interventions and policies to address health inequities.

Anna Hotton

Anna Hotton is a Research Assistant Professor in the Section of Infectious Diseases and Global Health at the University of Chicago Department of Medicine. She earned her B.S. degree at Cornell University and her MPH and Ph.D. at the School of Public Health at the University of Illinois at Urbana-Champaign. As staff scientist at the Chicago Center for HIV Elimination, Hutton studied the relationship between social factors and viral spread. Her DTI-funded project aims to adapt that work to COVID-19, using machine learning to identify data elements that are most important to include in modeling to better simulate various scenarios of disease spread and virtually test how different public health or social policy strategies can help mitigate the disease.

Jonathan Ozik

Jonathan Ozik is a Computational Scientist at Argonne National Laboratory and Senior Scientist in the Consortium for Advanced Science and Engineering at the University of Chicago where he develops applications of large-scale agent-based models, including models of infectious diseases, healthcare interventions, biological systems, water use and management, critical materials supply chains, and critical infrastructure. He also applies large-scale model exploration across modeling methods, including agent-based modeling, microsimulation and machine/deep learning. He leads the Repast project for agent-based modeling toolkits and the Extreme-scale Model Exploration with Swift (EMEWS) framework for large-scale model exploration capabilities on high performance computing resources.

March 18, 2021, 1 pm PT/4 pm ET

Building Structure Into Deep Learning

Zico Kolter, Associate Professor, Department of Computer Science, Carnegie Mellon University

Despite their wide applicability, deep learning systems often fail to exactly capture simple “known” features of many problem domains, such as those governed by physical laws or those that incorporate decision-making procedures. In this talk, I will present methods for these types of structural constraints — such as those associated with decision making, optimization problems, or physical simulation — directly into the predictions of a deep network. Our tool for achieving this will be the use of so-called “implicit layers” in deep models: layers that are defined implicitly in terms of conditions we would like them to satisfy, rather than via explicit computation graphs. l discuss how we can use these layers to embed (exact) physical constraints, robust control criteria, and task-based objectives, all within modern deep learning models. I will also highlight several applications of this work in reinforcement learning, control, energy systems, and other settings, and discuss generalizations and directions for future work in the area.


Zico Kolter is an Associate Professor in the Computer Science Department at Carnegie Mellon University, and also serves as Chief Scientist of AI Research for the Bosch Center for Artificial Intelligence. His work spans the intersection of machine learning and optimization, with a focus on developing more robust and rigorous methods in deep learning. In addition, he has worked in a number of application areas, highlighted by work on sustainability and smart energy systems. He is a recipient of the DARPA Young Faculty Award, a Sloan Fellowship, and Best Paper awards at NeurIPS, ICML (honorable mention), IJCAI, KDD, and PESGM.

March 11, 2021, 1 pm PT/4 pm ET

Using Data Science to Understand the Heterogeneity of SARS-COV-2 Transmission & COVID-19 Clinical Presentation in Mexico

Stefano Bertozzi, MD, Professor, School of Public Health, University of California, Berkeley

Juan Pablo Gutierrez, Professor at the Center for Policy, Population & Health Research, National Autonomous University of Mexico

In 2020, Mexico confirmed 1.5M cases of COVID-19, with 128,000 deaths — an 8.8 percent fatality rate that is among the highest worldwide. The positivity rate for those tested is 42 percent (WHO target = 5 percent). The pandemic is likely to become the main cause of death in 2020, and in 2021— even with the vaccine —mortality is expected to rise. Almost half of the Mexican population receives its medical care from the Mexican Social Security Institute (IMSS). Our team from UCB, IMSS, and UNAM aims to harness the massive patient-level clinical and socio-demographic data from the IMSS to better predict susceptibility to infection and serious complications among those who are infected. The advantages of working with the IMSS are clear – the disadvantage is that it has taken many months to get approval from the relevant human subjects and research committees. The IMSS comprises many poorly integrated data systems, so there is significant work involved in relating the disparate databases to each other. We now have 2.5 years of utilization data (outpatient visits [>300M], hospitalizations, prescriptions [almost 500M], and COVID tests). We will study variability by employer, by state and neighborhood, by household structure, by clinic, by provider (and provider behavior), by current and prior health conditions, by degree of control of chronic health conditions, by any drugs that they have been prescribed, as well as by the usual demographic and socioeconomic characteristics. The priority will be to identify modifiable factors that the IMSS can use to reduce population risk.

Stefano M. Bertozzi

Stefano M. Bertozzi is dean emeritus and professor of health policy and management at the UC Berkeley School of Public Health. He recently stepped down as the interim director of Alianza UCMX which integrates all UC systemwide programs with Mexico. Previously, he directed the HIV/TB programs at the Bill and Melinda Gates Foundation. At the Mexican National Institute of Public Health, he served as director of its Center for Evaluation Research and Surveys. He was the last director of the WHO Global Programme on AIDS and has also held positions with UNAIDS, the World Bank, and the government of the Democratic Republic of Congo. He currently serves as the founding editor-in-chief for Rapid Review: COVID-19, a new overlay journal that reviews COVID-19 research published by MIT Press. He holds a bachelor’s degree in biology and a PhD in health policy and management from MIT. He earned his medical degree at UCSD, and trained in internal medicine at UCSF.

Juan Pablo Gutierrez

Juan Pablo Gutierrez is Professor at the Center for Policy, Population & Health Research, National Autonomous University of Mexico (UNAM), Chair of the Technical Committee of the Morelos’ Commission on Evaluation of Social Development, and Member of GAVI Evaluation Advisory Committee. His research focuses on comprehensive evaluation of social programs and policies, universal health coverage and effective access, and social inequalities in health. He has been responsible for the evaluation of social and health programs in Mexico, Ecuador, Guatemala, Dominican Republic, Honduras, and India, as well as several population-based health surveys both in households and facilities. He is a member of the National Observatory on Health Inequalities in Mexico and has authored or co-authored more than 60 papers in peer-reviewed journals.

March 4, 2021, 1 pm PT/4 pm ET

Beyond Open Loop Thinking: A Prelude to Learning-Based Intelligent Systems

Lillian Ratliff, Assistant Professor, Department of Electrical and Computer Engineering, Adjunct Professor, Allen School of Computer Science and Engineering, University of Washington

Learning algorithms are increasingly being deployed in a variety of real world systems. A central tenet of present day machine learning is that when it is arduous to model a phenomenon, observations thereof are representative samples from some, perhaps unknown, static or otherwise independent distribution. In the context of systems such as civil infrastructure and other services (e.g., online marketplaces) dependent on its use, there are two central challenges that call into question the integrity of this tenet. First, (supervised) algorithms tend to be trained on past data without considering that the output of the algorithm may change the environment, and hence the data distribution. Second, data used to either train algorithms offline or as input to online decision-making algorithms may be generated by strategic data sources such as human users. Indeed, such data depends on how the algorithm impacts a user’s individual objectives or (perceived) quality of service, which leads to the underlying data distribution being dependent on the output of the algorithm. This begs the question of how learning algorithms can and should be designed taking into consideration this closed-loop interaction with the environment in which they will be deployed. This talk will provide one perspective on designing and analyzing algorithms by modeling the underlying learning task in the language of game theory and control, and using tools from these domains to provide performance guarantees and highlight recent, promising results in this direction.


Lillian Ratliff obtained her PhD in Electrical Engineering and Computer Sciences from the University of California, Berkeley in 2015. Prior to that Lillian obtained an MS in Electrical Engineering (2010) and BS degrees in Mathematics and Electrical Engineering (2008) all from the University of Nevada, Las Vegas. Her research interests lie at the intersection of learning, optimization, and game theory. She is the recipient of a National Science Foundation Graduate Research Fellowship (2009), CISE Research Initiation Initiative Award (2017), and CAREER Award (2019). She is also a recipient of the 2020 Office of Naval Research Young Investigator award and the Dhanani Endowed Faculty Fellowship (2020).

February 25, 2021, 1 pm PT/4 pm ET

Mad Max: Affine Spline Insights into Deep Learning

Richard Baraniuk, Victor E. Cameron Professor of Electrical and Computer Engineering, Rice University

We build a rigorous bridge between deep networks (DNs) and approximation theory via spline functions and operators. Our key result is that a large class of DNs can be written as a composition of max-affine spline operators (MASOs), which provide a powerful portal through which to view and analyze their inner workings. For instance, conditioned on the input signal, the output of a MASO DN can be written as a simple affine transformation of the input. This implies that a DN constructs a set of signal-dependent, class-specific templates against which the signal is compared via a simple inner product; we explore the links to the classical theory of optimal classification via matched filters and the effects of data memorization. The spline partition of the input signal space that is implicitly induced by a MASO directly links DNs to the theory of vector quantization (VQ) and K-means clustering, which opens up new geometric avenue to study how DNs organize signals in a hierarchical and multiscale fashion.


Richard G. Baraniuk is the Victor E. Cameron Professor of Electrical and Computer Engineering at Rice University and the Founding Director of OpenStax. His research interests lie in new theory, algorithms, and hardware for sensing, signal processing, and machine learning. He is a Fellow of the American Academy of Arts and Sciences, National Academy of Inventors, American Association for the Advancement of Science, and IEEE. He has received the DOD Vannevar Bush Faculty Fellow Award (National Security Science and Engineering Faculty Fellow), the IEEE Signal Processing Society Technical Achievement Award, and the IEEE James H. Mulligan, Jr. Education Medal, among others.

February 18, 2021, 1 pm PT/4 pm ET

Why Do ML Models Fail?

Aleksander Madry, Professor of Computer Science, Massachusetts Institute of Technology

Our current machine learning (ML) models achieve impressive performance on many benchmark tasks. Yet, these models remain remarkably brittle, susceptible to manipulation and, more broadly, often behave in ways that are unpredictable to users. Why is this the case? In this talk, we identify human-ML misalignment as a chief cause of this behavior. We then take an end-to-end look at the current ML training paradigm and pinpoint some of the roots of this misalignment. We discuss how current pipelines for dataset creation, model training, and system evaluation give rise to unintuitive behavior and widespread vulnerability. Finally, we conclude by outlining possible approaches towards alleviating these deficiencies.


Aleksander Madry is a Professor of Computer Science at MIT and leads the MIT Center for Deployable Machine Learning. His research interests span algorithms, continuous optimization, science of deep learning, and understanding machine learning from a robustness and deployability perspectives. Aleksander’s work has been recognized with a number of awards, including an NSF CAREER Award, an Alfred P. Sloan Research Fellowship, an ACM Doctoral Dissertation Award Honorable Mention, and Presburger Award. He received his PhD from MIT in 2011 and, prior to joining the MIT faculty, he spent time at Microsoft Research New England and on the faculty of EPFL.

February 11, 2021, 1 pm PT/4 pm ET

Scoring Drugs: Small Molecule Drug Discovery for COVID-19 using Physics-Inspired Machine Learning

Teresa Head-Gordon, Chancellor’s Professor, Department of Chemistry, Chemical and Biomolecular Engineering, and Bioengineering, University of California, Berkeley

The rapid spread of SARS-CoV-2 has spurred the scientific world into action for therapeutics to help minimize fatalities from COVID-19. Molecular modeling is combating the current global pandemic through the traditional process of drug discovery, but the slow turnaround time for identifying leads for antiviral drugs, analyzing structural effects of genetic variation in the evolving virus, and targeting relevant virus-host protein interactions is still a great limitation during an acute crisis. The first component of drug discovery – the structure of potential drugs and the target proteins – has driven functional insight into biology ever since Watson, Crick, Franklin, and Wilkins solved the structure of DNA. What could we do with structural models of host and virus proteins and small molecule therapeutics? We can further enrich structure with dynamics for discovery of new surface sites exposed by fluctuations to bind drugs and peptide therapeutics not revealed by a static structural model. These “cryptic” binding sites offer new leads in drug discovery but will only yield fruit if they can be assessed rapidly for binding affinity for new small molecule drugs. We offer physics-inspired data-driven models to: 1) extend the chemical space of new drugs beyond those available; 2) create reliable scoring functions to evaluate drug binding affinities to cryptic binding sites of COVID-19 targets; 3) accelerate computation of binding affinities by training machine learning models; and 4) closing the loop of design and evaluation to bias the distribution of new drug candidates towards desired metrics enabled by the C3 AI Suite.


The simultaneous revolutions in energy, molecular biology, nanotechnology, and advanced scientific computing is giving rise to new interdisciplinary research opportunities in theoretical and computational chemistry. The research interests of the Teresa Head-Gordon lab embraces this large scope of science drivers through the development of general computational models and methodologies applied to molecular liquids, macromolecular assemblies, protein biophysics, and homogeneous, heterogeneous catalysis and biocatalysis. She has a continued and abiding interest in the development and application of complex chemistry models, accelerated sampling methods, coarse graining, and multiscale techniques, analytical and semi-analytical solutions to the Poisson-Boltzmann Equation, and advanced self-consistent field (SCF) solvers and SCF-less methods for many-body physics. The methods and models developed in her lab are widely disseminated through many community software codes that scale on high performance computing platforms.

February 4, 2021, 1 pm PT/4 pm ET

Triaging of COVID-19 Patients from Audio-Visual Cues

Narendra Ahuja, Research Professor of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign

The COVID-19 pandemic has placed unprecedented stress on hospital capacity. Increased emergency department (ED) patient volumes and admission rates have led to a scarcity in beds. Bed-sparing protocols that identify COVID-19 patients stable for discharge from the ED or early hospital discharge have proven elusive given this population’s propensity to rapidly deteriorate up to one week after illness onset. Consequently, a significant number of stable patients are unnecessarily admitted to the hospital while some discharged patients decompensate at home and subsequently require emergency transport to the ED. In order to conserve hospital beds, there is an urgent need for improved methods for assessing clinical stability of COVID-19 patients. In this talk, we will describe our project’s immediate goal to develop audiovisual tools to reproduce common physical exam findings. These will be subsequently used to predict clinical decompensation from patient videos captured using consumer grade smartphones. These tools will be tested on COVID-19 and other pulmonary patient populations. We will start collecting patient data at UIC and UC hospitals in January 2021 and are developing explainable artificial intelligence and machine learning algorithms for predicting impending deterioration from health-relevant audiovisual features and provide explanations in terms of the clinical details within the electronic health record. Once validated on our patient data, the tools will provide clinical assessments of COVID-19 patients both at the bedside and across telemedicine platforms during virtual follow-ups. The techniques and algorithms developed in this project are likely to be applicable to other high-risk patient populations and emerging platforms, such as telemedicine.

Narendra Ahuja

Narendra Ahuja is a Research Professor of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign. His research is in Artificial Intelligence fields of computer vision, pattern recognition, machine learning, and image processing and their applications, including problems in developing societies. He has co-authored more than 400 papers in journals and conferences and supervised the research of more than 50 PhD, 15 MS, 100 undergraduates, and 10 Postdoctoral Scholars. He received his Ph.D. from the University of Maryland, College Park, in 1979. He is a fellow of the Institute of Electrical and Electronics Engineers, the American Association for Artificial Intelligence, the International Association for Pattern Recognition, the Association for Computing Machinery, the American Association for the Advancement of Science, and the International Society for Optical Engineering.

January 28, 2021, 1 pm PT/4 pm ET

Modeling and Managing the Spread of COVID-19

Subhonmesh Bose, Assistant Professor, Electrical and Computer Engineering, University of Illinois at Urbana-Champaign

Testing and lock-down provide two important control levers to combat the spread of an infectious disease. Testing is a targeted instrument that permits the isolation of infectious individuals. Lock-down, on the other hand, is blunt and restricts the mobility of all people. In the first part of the talk, I will present a compartmental epidemic model that accounts for asymptomatic disease transmission, the impact of lock-down and different kinds of testing, motivated by the nature of the ongoing COVID-19 outbreak. In the large population regime, static mobility levels and testing requirements are characteristics that can mitigate the disease spread asymptotically. Then, I present interesting properties of an optimal dynamic lock-down and testing strategy that minimizes a detailed cost of the epidemic. In the second part of the talk, I adapt the model for small populations, such as that of an educational institution, and use data from the UIUC SHIELD program’s rapid saliva-based testing strategy to estimate model parameters. Reopening strategies for educational institutions are evaluated via agent-based simulations using said parameter estimates. This talk is based on joint work with U. Mukherjee, S. Seshadri, S. Souyris, A. Ivanov, Y. Xu, and R. Watkins.


Subhonmesh Bose is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign. His research is in the area of power and energy systems and is geared towards enabling the integration of renewable and distributed energy resources in the modern power grid. He is interested in developing rigorous analytical frameworks, fast algorithmic architectures, and efficient market designs to help enable that integration.

January 14, 2021, 1 pm PT/4 pm ET

A Bayesian Hierarchical Network for Combining Heterogeneous Data Sources in Medical Diagnoses – With Applications to COVID-19

Claire Donnat, Professor, University of Chicago

The increasingly widespread use of affordable, yet often less reliable medical data and diagnostic tools poses a new challenge for the field of ComputerAided Diagnosis: how can we combine multiple sources of information with varying levels of precision and uncertainty to provide an informative diagnosis estimate with confidence bounds? Motivated by a concrete application in lateral flow antibody testing, we devise a Stochastic Expectation-Maximization algorithm that allows the principled integration of heterogeneous and potentially unreliable data types. Our Bayesian formalism is essential in (a) flexibly combining these heterogeneous data sources and their corresponding levels of uncertainty, (b) quantifying the degree of confidence associated with a given diagnostic, and (c) dealing with the missing values that typically plague medical data. We quantify the potential of this approach on simulated data, and showcase its practicality by deploying it on a real COVID19 immunity study.


Claire Donnat is an Assistant Professor in the Department of Statistics at the University of Chicago. Her work focuses on high-dimensional and Bayesian statistics, and their applications to biomedical data. Prior to the University of Chicago, she completed her PhD in Statistics at Stanford where she was advised by Professor Susan Holmes.

December 10, 2020, 1 pm PT/4 pm ET

Housing Precarity, Eviction, and Inequality in the Wake of COVID-19

Karen Chapple, Professor and Chair of City & Regional Planning, University of California, Berkeley

Tim Thomas, Research Director, Urban Displacement Project, University of California, Berkeley

Peter Hepburn, Assistant Professor of Sociology, Rutgers University-Newark

COVID-19 has the potential to exacerbate a severe housing and economic crisis in the United States, which will in turn undercut public health responses to the pandemic. Ensuring housing security is vital to mitigating the spread of the virus and sustaining health, economic security, and family stability. This joint, interdisciplinary project between the University of California, Berkeley and Princeton University brings together a group of academics and data scientists to track, analyze, and respond to pandemic-driven spikes in eviction and displacement risks. Doing so requires two central elements, both of which rely heavily on data science tools and methodologies. First, we have developed the Eviction Tracking System, an innovative tool for tracking real-time eviction filings in more than a dozen cities across the U.S. Second, we have developed a housing precarity risk model using machine learning that allows us to better analyze and predict areas at disproportionate risk of eviction, displacement, unemployment, and infection in the wake of the COVID-19 pandemic. This project provides major new sources of data that serve to inform research and public policy regarding housing and inequality in America.


Karen Chapple, Ph.D., is a city planner by training who studies inequalities in the planning, development, and governance of regions in the U.S. and Latin America, with a focus on economic development and housing. Her most recent book is Transit-Oriented Displacement or Community Dividends? Understanding the Effects of Smarter Growth on Communities.

Version 2

Tim Thomas is an urban sociologist, demographer, and data scientist. His research examines how neighborhood change impacts racial and gender disparities in housing, segregation, and forced mobility. His work has been published in academic journals and used as evidence to inform civil and state housing law.


Peter Hepburn is a sociologist and demographer. His research examines how changes to three core social institutions — work, criminal justice, and housing — serve to produce and perpetuate inequality. His work has been published in Social Forces, Demography, Social Problems, and the Journal of Marriage and Family.

December 3, 2020, 1 pm PT/4 pm ET

Stochastic Optimization of Inventory at Large-scale Supply Chains

Mehdi Maasoumy, Principal Data Scientist,

Companies managing physical goods face growing supply chain challenges, given accelerated business cycles, stochasticity in supply and demand, and complex, interdependent, global supply chains. Enterprises often use inventory buffers – for raw materials, work-in-process goods, and finished products – as a way to help them manage service levels, and on-time and in full (OTIF) metrics. However, holding excess inventory often complicates business operations, and can lock up billions of dollars of capital that could be otherwise deployed.

Most manufacturing companies have historically deployed advanced Manufacturing Resource Planning (MRP) software, however, most commercially available MRP solutions do not result in optimal solutions for modern enterprises.

The C3 AI Inventory Optimization application fundamentally re-formulates and solves the supply chain and inventory problem as a constrained stochastic optimization problem. Our goal is to find the optimal re-order parameters that minimize inventory levels subject to a pre-defined service-level constraint and other operational constraints. The output of our approach can be the optimal placement of orders or the optimal inputs into an MRP system to ensure that the MRP heuristic then results in the right material levels and production operations.

Using C3 AI Inventory Optimization, we have helped our customers achieve inventory reductions of 30-50 percent‚ saving hundreds of millions of dollars at major enterprises at a global scale.

Mehdi Maasoumy
Mehdi Maasoumy is a Principal Data Scientist at, where he is leading AI teams that develop machine learning, deep learning, and optimization algorithms to solve previously unsolvable business problems — including Stochastic Inventory Optimization of Supply Chain and Predictive Maintenance across a wide range of industries such as Oil and Gas, Manufacturing, Energy, and Healthcare. Mehdi holds a M.Sc. and Ph.D. from the University of California at Berkeley and a B.Sc. from Sharif University of Technology, and is the recipient of three best paper awards from ACM and IEEE.

November 19, 2020, 1 pm PT/4 pm ET

Tracking the Few and Far Between: Computational Strategies to Speed the Discovery of Low-frequency Genomic Variation in COVID-19

Nancy Amato, Head of the Department of Computer Science and Abel Bliss Professor of Engineering, University of Illinois at Urbana-Champaign

Lawrence Rauchwerger, University of Illinois at Urbana-Champaign

Todd J. Treangen, Rice University

To date, the vast majority of COVID-19 genomic research has been focused on a high-level view of SARS-CoV-2 diversity, overlooking the diversity of the viral population that exists within each COVID-19 positive patient. While viral load of SARS-CoV-2 in an individual can exceed hundreds of thousands of copies, available genomic databases only contain a single consensus version of this diverse population, discarding any low-frequency mutations. The goal of our project, CoVariants, is to develop novel computational approaches to recover these discarded variants and allow for rapid characterization of within-host diversity of SARS-CoV-2 across tens of thousands of samples. Commonly used computational tools either are not designed for the detection of low-frequency variants within viral populations, or require significant computational resources per sample. In this talk, we will describe how new parallelization strategies and approximate statistical methods can reduce the computational requirements of a widely used existing approach by up to 400 percent while preserving 100 percent of the low-frequency genomic diversity. We will end our talk by highlighting how we plan to use these improved computational methods to provide insight into the biological underpinnings of SARS-CoV-2 transmissibility and severity compared to other coronaviruses.


Nancy M. Amato is Abel Bliss Professor and Department Head of Computer Science at the University of Illinois. She received undergraduate degrees in Mathematical Sciences and Economics from Stanford, and M.S. and Ph.D. degrees in Computer Science from UC Berkeley and the University of Illinois, respectively. Her research focuses on robotics motion planning, computational biology and geometry, and parallel computing. Amato received the 2019 IEEE RAS Leadership Award in Robotics and Automation, the 2014 CRA Habermann Award, and the inaugural NCWIT Harrold/Notkin Research and Graduate Mentoring Award in 2014. She is a Fellow of the AAAI, AAAS, ACM, and IEEE.


Lawrence Rauchwerger is a professor in the Department of Computer Science at the University of Illinois. Previously, he was the Eppright Professor of Computer Science and Engineering at Texas A&M University and co-Director of the Parasol Lab. He received an engineering degree from the Polytechnic Institute Bucharest, a M.S. in Electrical Engineering from Stanford University and a Ph.D. in Computer Science from the University of Illinois. His approach to auto-parallelization, thread-level speculation and parallel code development has influenced industrial products at corporations including IBM, Intel, and Sun. Rauchwerger is a Fellow of the AAAS and IEEE and has received an NSF CAREER Award, awards from IBM and Intel.

ToddTreangen 500x500

Todd J. Treangen, Ph.D. is an Assistant Professor in the Department of Computer Science at Rice University and co-lead of the COVID-19 International Research Team. Before joining Rice, Dr. Treangen was a Research Scientist at the University of Maryland College Park. He received his Ph.D. in Computer Science in 2008 from the Polytechnic University of Catalonia (Barcelona, Spain). His research group focuses on solving large-scale computational problems specific to computational biology, with a focus on developing robust software tools targeted towards biothreat screening, infectious disease monitoring, and microbial forensics.

November 12, 2020, 1 pm PT/4 pm ET

Mathematics of Deep Learning

René Vidal, Herschel Seder Professor of Biomedical Engineering and Inaugural Director of the Mathematical Institute for Data Science, Johns Hopkins University

The past few years have seen a dramatic increase in the performance of recognition systems, thanks to the introduction of deep networks for representation learning. However, the mathematical reasons for this success remain elusive. For example, a key issue is that the neural network training problem is non-convex, hence optimization algorithms may not return a global minima. In addition, the regularization properties of algorithms such as dropout remain poorly understood. The first part of this talk will overview recent work on the theory of deep learning that aims to understand how to design the network architecture, how to regularize the network weights, and how to guarantee global optimality. The second part of this talk will present sufficient conditions to guarantee that local minima are globally optimal and that a local descent strategy can reach a global minima from any initialization. Such conditions apply to problems in matrix factorization, tensor factorization, and deep learning. The third part of this talk will present an analysis of the optimization and regularization properties of dropout for matrix factorization in the case of matrix factorization.

Rene Vidal

René Vidal is the Herschel Seder Professor of Biomedical Engineering and Director of the Mathematical Institute for Data Science at Johns Hopkins University. He is also an Amazon Scholar, Chief Scientist at NORCE, and Associate Editor in Chief of TPAMI. His current research focuses on the foundations of deep learning and its applications in computer vision and biomedical data science. He is an AIMBE Fellow, IEEE Fellow, IAPR Fellow, and Sloan Fellow, and has received numerous awards for his work, including the D’Alembert Faculty Award, J.K. Aggarwal Prize, ONR Young Investigator Award, NSF CAREER Award, and best paper awards in machine learning, computer vision, controls, and medical robotics.

November 5, 2020, 1 pm PT/4 pm ET

Reconstructing SARS-COV-2 Response Pathways

Ziv Bar-Joseph, FORE Systems Professor of Computer Science, Carnegie Mellon University

SARS-CoV-2 is known to primarily impact cells via two viral entry factors, ACE2 and TMPRSS2. However, much less is currently known about virus activity within cells. We used computational methods based on probabilistic graphical models to integrate several recent SARS-CoV-2 interaction and expression datasets with general protein-protein and protein-DNA interaction datasets. The reconstructed models display the pathways viral proteins use to drive expression in human cells and the pathways the cell uses to respond to the infection. Intersecting key proteins on these pathways with expression data from underlying conditions shown to increase mortality from SARS-CoV-2, and with knockout and phosphorylation data, identifies a few potential targets for treating cells to reduce viral loads.

Screen Shot 2020-10-30 at 7.28.39 PM

Ziv Bar-Joseph is the FORE Systems Professor of Computational Biology and Machine Learning at Carnegie Mellon University. His work focuses on the development of machine learning methods for the analysis, modeling, and visualization of time series high throughput biological data. Dr. Bar-Joseph is the recipient of the Overton Prize, an NSF CAREER Award, and several conference Best Paper awards. He is currently leading the Computational Tools Center for the National Institutes of Health Human BioMolecular Atlas Program (HuBMAP). He has served on the advisory board of several national efforts including the National Institute for Allergy and Infectious Diseases Systems Biology Program. Software tools developed by his group are widely used for the analysis of genomics data.

October 29, 2020, 1 pm PT/4 pm ET

Reliable Predictions? Counterfactual Predictions? Equitable Treatment? Some Recent Progress in Predictive Inference

Emmanuel Candès, Barnum-Simons Chair in Mathematics and Statistics, Professor of Statistics, and Professor, by courtesy, of Electrical Engineering, Stanford University

Recent progress in machine learning provides us with many potentially effective tools to learn from datasets of ever increasing sizes and make useful predictions. How do we know that these tools can be trusted in critical and high-sensitivity systems? If a learning algorithm predicts the GPA of a prospective college applicant, what guarantees do I have concerning the accuracy of this prediction? How do we know that it is not biased against certain groups of applicants? This talk introduces statistical ideas to ensure that the learned models satisfy some crucial properties, especially reliability and fairness (in the sense that the models need to apply to individuals in an equitable manner). To achieve these important objectives, we shall not “open up the black box” and try understanding its underpinnings. Rather, we discuss broad methodologies that can be wrapped around any black box to produce results that can be trusted and are equitable. We also show how our ideas can inform causal inference predictive. For instance, we will answer counterfactual predictive problems (i.e., predict what the outcome would have been if a patient had not been treated).

Emmanuel Candes, Dept. of Statistics

Emmanuel Candès is the Barnum-Simons Chair in Mathematics and Statistics, a Professor of Electrical Engineering (by courtesy), and a member of the Institute of Computational and Mathematical Engineering, all at Stanford University. Earlier, Candès was the Ronald and Maxine Linde Professor of Applied and Computational Mathematics at the California Institute of Technology. His research interests are in computational harmonic analysis, statistics, information theory, signal processing, and mathematical optimization with applications to the imaging sciences, scientific computing, and inverse problems. Candès has given over 60 plenary lectures in mathematics and statistics, biomedical imaging, and solid-state physics. Candès was awarded the Alan T. Waterman Award from the National Science Foundation and was elected to the National Academy of Sciences and the American Academy of Arts and Sciences in 2014.

October 22, 2020, 1 pm PT/4 pm ET

Machine Learning-based Design of Proteins, Small Molecules, and Beyond

Jennifer Listgarten, Professor, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley

Data-driven design is making headway into a number of application areas, including protein, small-molecule, and materials engineering. The design goal is to construct an object with desired properties, such as a protein therapeutic that binds tightly to its target. To that end, costly experimental measurements are being replaced with calls to a high-capacity regression model trained on labeled data, which can be leveraged in an in silico search for promising design candidates. The aim then is to discover designs that are better than the best design in the observed data. This goal puts machine learning-based design in a much more difficult spot than traditional applications of predictive modelling, since successful design requires, by definition, some degree of extrapolation–a pushing of the predictive models to its unknown limits, in parts of the design space that are a priori unknown. In this talk, I will anchor this overall problem in protein engineering and discuss our emerging approaches to tackle it.

Jennifer Listgarten

Jennifer Listgarten is a Professor in the Department of Electrical Engineering and Computer Sciences and the Center for Computational Biology at the University of California, Berkeley. She is also a member of the steering committee for the Berkeley AI Research (BAIR) Lab and a Chan Zuckerberg investigator. From 2007 to 2017, she was at Microsoft Research in Cambridge, MA (2014-2017), Los Angeles (2008-2014), and Redmond, WA (2007-2008). She completed her Ph.D. in the machine learning group in the Department of Computer Science at the University of Toronto, located in her hometown. She has two undergraduate degrees, one in Physics and one in Computer Science, from Queen’s University in Kingston, Ontario. Jennifer’s research interests are broadly at the intersection of machine learning, applied statistics, molecular biology, and science.

October 15, 2020 1 pm PT/4 pm ET

COVIDScholar: Applying Natural Language Processing at Scale to Accelerate COVID-19 Research

Gerbrand Ceder, Chancellor’s Professor, Department of Materials Science and Engineering, University of California, Berkeley

Amalie Trewartha, Postdoctoral Scholar, Division of Materials Science, Lawrence Berkeley National Laboratory

There is a critical need for tools that can help the COVID-19 researchers stay on top of the emerging literature and identify critical connections between ideas and observations that could lead to effective vaccines and therapies for COVID-19. To this end, our team at UC Berkeley and Lawrence Berkeley National Laboratory is building, a knowledge portal tailored specifically for COVID-19 research that leverages natural language processing (NLP) techniques to synthesize the information spread across more than 140,000 emergent research articles, patents, and clinical trials into actionable insights and new knowledge. Having its origins in our text-processing work in Materials Science, COVIDScholar is powered by an automated system that scrapes research documents from dozens of sources across the internet, cleans/repairs metadata as necessary, and analyzes the text with a number of NLP models for classification, information extraction, and scientific language modeling. We then integrate this information with specialized knowledge graphs which has the potential to give users unparalleled insight into the complex interactions that govern the transmission of COVID-19, the disease’s progression, and potential therapeutic strategies. This approach to combining textual information, such as word embeddings, with ontological knowledge graphs has the potential to improve the performance of machine learning models that operate on these data structures and to enable new ways of exploring literature on emerging subjects by leveraging past knowledge more efficiently.

Gerbrand Ceder

Gerbrand Ceder is the Chancellor’s Professor of Materials Science and Engineering at the University of California, Berkeley. His research is in computational and experimental materials design for clean energy technology and in Materials Genome approaches to materials design and synthesis. He has published over 400 scientific papers and holds more than 20 U.S. and foreign patents. He is a member of the U.S. National Academy of Engineering and the Royal Flemish Academy of Belgium for Science and The Art, a Fellow of the Materials Research Society and the Minerals, Metals & Materials Society, and has received awards from the Electrochemical Society, the Materials Research Society, the Minerals, Metals & Materials Society, and the International Battery Association. He is Co-Lead Scientist for new battery technologies at the U.S. Department of Energy’s Joint Center for Energy Storage (JCESR) and Chief Scientist of the Energy Frontier Research Center at the National Renewable Energy Laboratory (NREL).

Amelie Trewartha

Amelie Trewartha is a postdoctoral scholar in Gerbrand Ceder’s group at Lawrence Berkeley National Laboratory. She began her career as a nuclear physicist, before moving into materials science in 2019, with a focus on machine learning. Her research interests include the application of natural language processing (NLP) techniques to scientific literature, and building thermodynamically-motivated machine learning models for materials property prediction.

October 8, 2020, 1 pm PT/4 pm ET

Solving “Prediction Problems” in Health, from Heart Attacks to COVID-19

Ziad Obermeyer, Associate Professor of Health Policy and Management, University of California, Berkeley

In order to treat a disease, doctors must first know whether it is present. Thus, a key task in medicine is to judge the likelihood of a disease given rich, observable patient data. Because this resembles the prediction tasks where machine learning algorithms shine, we use them to study two important clinical problems. The first is the decision to test for heart attack. Because a test is only useful if it yields new information, efficient testing is grounded in accurate prediction of test outcomes. By comparing doctors’ testing decisions to tailored algorithmic predictions, we show that doctors both over-test (52.6% of high-cost tests for heart attack are wasted) and also under-test (many patients with predictably high risk go untested, then go on to experience frequent adverse cardiac events including death in the next 30 days). The second is the study of triage decisions in COVID-19. In emergency rooms across the world, doctors must decide if patients with suspected or confirmed disease are safe to go home, or if they need hospital-level monitoring. Clinicians have noted that many patients are tragically sent home, only to deteriorate rapidly. In ongoing work, we use machine vision to find subtle predictors of pulmonary collapse that human doctors miss. Together, these examples suggest that training algorithms to solve clinical “prediction problems” can yield both improvements in clinical care, and new insights into physician behavior and human health. 


Ziad Obermeyer is an Associate Professor at the University of California, Berkeley, where he does research at the intersection of machine learning, medicine, and health policy. He was named an Emerging Leader by the National Academy of Medicine and has received numerous awards including the Early Independence Award — the National Institutes of Health’s most prestigious award for exceptional junior scientists — and the Young Investigator Award from the Society for Academic Emergency Medicine. Previously, he was an Assistant Professor at Harvard Medical School. He continues to practice emergency medicine in underserved communities.

October 1, 2020, 1 pm PT/4 pm ET

Improving Fairness & Equity in Policy Applications of Machine Learning

Rayid Ghani, Distinguished Career Professor in the Machine Learning Department and the Heinz College of Information Systems and Public Policy, Carnegie Mellon University

We are in the early stages of using AI, ML, and Data Science to help make better policy decisions. Governments and nonprofits have started to explore how to improve society by tackling problems such as preventing children from getting lead poisoning, reducing police violence and misconduct, and increasing vaccination rates. As the impact of the COVID-19 pandemic has continued to increase, both ML researchers and practitioners have been proposing and developing methods to better understand, predict, and mitigate the spread, and governments have been exploring the use of these tools to better guide policy decisions. The AI and ML tools will hopefully be important elements of society’s efforts to overcome COVID-19, but as with any application of machine learning and AI, they also pose risks of introducing or exacerbating disparities. In this talk, I’ll give examples of recent work that highlights the use of ML/AI to achieve fair and equitable outcomes and challenges that need to be tackled in order to have social and policy impact in a fair and equitable manner.


Rayid Ghani is a Distinguished Career Professor in the Machine Learning Department and the Heinz College of Information Systems and Public Policy at Carnegie Mellon University. Rayid is a reformed computer scientist and wanna-be social scientist, focused on using large-scale Artificial Intelligence/Machine Learning/Data Science to solve public policy and social challenges in a fair and equitable manner. Rayid works with governments and non-profits on policy in health, criminal justice, education, public safety, economic development, and urban infrastructure. Rayid is passionate about teaching practical data science and started the Data Science for Social Good Fellowship that trains computer scientists, statisticians, and social scientists to work on data science problems with social impact. Before joining Carnegie Mellon University, Rayid was the Founding Director of the Center for Data Science & Public Policy, a Research Associate Professor in Computer Science, a Senior Fellow at the Harris School of Public Policy at the University of Chicago, and Chief Scientist of the Obama 2012 Election Campaign.

September 24, 2020, 1 pm PT/4 pm ET

Towards AI for Healthcare with Applications to the COVID-19 Pandemic

Sanmi Koyejo, Assistant Professor, Department of Computer Science, University of Illinois at Urbana-Champaign

With the emergence of public healthcare crises such as the COVID-19 Pandemic, it is increasingly evident that AI is among the most powerful tools for addressing early detection of diseases, triage, treatment planning, and patient management, among many other pressing healthcare problems. What will it take to build effective machine learning systems for healthcare? This talk will outline our research progress towards answering this question. To this end, I will present emerging technical advances in federated learning, modeling, evaluation, privacy, and trustworthiness. I will also outline how we are bringing these tools to bear to aid in analyzing medical images from COVID-19 patients.


Sanmi Koyejo is an Assistant Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign. Koyejo’s research interests are in developing the principles and practice of adaptive and robust machine learning. Additionally, Koyejo focuses on applications to neuroscience and biomedical imaging. Koyejo has been the recipient of several awards including a best paper award from the conference on uncertainty in artificial intelligence (UAI), a Kavli Fellowship, an IJCAI early career spotlight, and a trainee award from the Organization for Human Brain Mapping (OHBM). Koyejo serves on the board of the Black in AI organization.

September 17, 2020, 1 pm PT/4 pm ET

Impact of Mobility on Epidemic Spread: Some Lessons from NYC and India

Saurabh Amin, Robert N. Noyce Career Development Associate Professor of Civil and Environmental Engineering, MIT

In this talk, we analyze the impact of mobility services (in particular, public transportation systems) on the spread of COVID-19. We also propose testing strategies based on mobility between areas with heterogeneous risk levels to control disease transmission. Our work focuses on two distinct regions: (1) NYC – where a significant number of people rely on the MTA for their daily commute; and (2) Odisha – an eastern state in India which saw a significant influx of migrant workers from COVID hotspots. In both regions, high levels of human mobility and limited testing capacity led to a rapid increase of COVID cases. In the study of NYC, we run panel analysis to evaluate the relative impact of MTA ridership over general mobility on the growth in cases at the zipcode level. We find strong heterogeneities across zip codes, which can be explained by socioeconomic factors and unbalanced testing resources. Importantly, we find that while a higher level of general mobility is associated with an increase in cases, the MTA usage did not lead to additional growth in cases after April. In contrast, the district-level data from Odisha exhibits strong correlation between case growth and volume of incoming migrant workers from high-risk states after May. We construct an optimization model that allows the state health authority to effectively allocate testing resources to worker populations based on the heterogeneous risk levels at their origin states and the local district population. This work is joint with Manxi Wu, Isabel Munoz, Devendra Shelar, and R. Gopalakrishnan.


Saurabh Amin is an Associate Professor in the Department of Civil and Environmental Engineering at MIT. He is affiliated with the Laboratory for Information and Decision Systems (LIDS) and the Operations Research Center at MIT. He received his PhD in Systems Engineering from UC Berkeley (2011), M.S.E. from UT Austin (2004), and B.Tech. from IIT Roorkee (2002). His fields of expertise include stochastic control theory, applied game theory, and optimization in networks. His research focuses on the design of high-confidence monitoring and control algorithms for infrastructure systems. He is a recipient of an NSF CAREER Award, the Google Faculty Research Award, the Robert N. Noyce Professorship, and the Ole Madsen Mentoring Award. 

September 10, 2020, 1 pm PT/4 pm ET

Evolutionary Adaptations and Spreading Processes in Complex Networks

H. Vincent Poor, Michael Henry Strater University Professor of Electrical Engineering, Princeton University

A common theme among many models for spreading processes in networks is the assumption that the propagating object (e.g., a pathogen, in the context of infectious disease propagation, or a piece of information, in the context of information propagation) is transferred across network nodes without going through any modification. However, in real-life spreading processes, pathogens often evolve in response to changing environments or medical interventions, and information is often modified by individuals before being forwarded. In this talk, we will discuss the effects of such adaptations on spreading processes in complex networks with the aim of revealing their role in determining the threshold, probability, and final size of epidemics, and exploring the interplay between them and the structural properties of the network.


H. Vincent Poor is the Michael Henry Strater University Professor of Electrical Engineering at Princeton University, where he is engaged in research in information theory, machine learning and network science, and their applications in wireless networks, energy systems, and related fields, including recently modeling the spread of the COVID-19 epidemic. He is a member of the National Academy of Engineering and the National Academy of Sciences, and a foreign member of the Chinese Academy of Sciences and the Royal Society. Recognition of his work includes the 2017 IEEE Alexander Graham Medal and honorary doctorates from universities in Asia, Europe, and North America.

September 3, 2020, 1 pm PT/4 pm ET

Metapopulation and Age-Structured Epidemic Models for the COVID-19 Pandemic

Zoi Rapti, Associate Professor, Department of Mathematics, University of Illinois at Urbana-Champaign

In this colloquium, Zoi Rapti will first address the issue of parameter identifiability from reported data, such as confirmed cases and deaths. Parameter identifiability analysis is used to determine whether unknown parameters in ordinary differential equation models can be determined from the available data. She will then introduce age-structured and spatial (metapopulation) models for the spread of COVID-19, demonstrating that in some multi-group models that are structured by age, the basic reproductive number of each group is smaller than the basic reproductive number of the entire community. Hence, in most cases, it is not informative to consider separately groups that are known to interact, as this may underestimate the overall severity of the outbreak. In metapopulation models, she will show how traffic data is used in mobility models of epidemic spread. Rapti’s talk represents joint work of a research team that includes Eleftheria Kontou (Civil and Environmental Engineering, University of Illinois, Urbana-Champaign), Yannis Kevrekidis (Chemical and Biomolecular Engineering & Applied Mathematics and Statistics, Johns Hopkins University), and P. G. Kevrekidis (Mathematics and Statistics, University of Massachusetts at Amherst).


Zoi Rapti is an Associate Professor in the Department of Mathematics at the University of Illinois, Urbana-Champaign and the Carle R. Woese Institute for Genomic Biology. Her research focus is on nonlinear dynamics with applications to mathematical biology (DNA denaturation, epidemiology, community assembly, phage-bacteria interactions, data-theory coupling) and physics (Nonlinear Schrodinger-type equations, discrete Klein-Gordon equations).  She holds a bachelor’s degree in Mechanical Engineering from the National Technical University of Athens, Greece and a PhD in Mathematics from the University of Massachusetts, Amherst.

August 27, 2020, 1 pm PT/4 pm ET

Targeted Dynamic Interventions in Networked Epidemic Models

Asuman Ozdaglar, Distinguished Professor of Engineering Department Head, Electrical Engineering and Computer Science, Deputy Dean of Academics, Schwarzman College of Computing, MIT

Francesca Parise, Assistant Professor, Electrical and Computer Engineering, Cornell University

Epidemic spread models are playing an increasingly central role for policy making in the COVID-19 pandemic. Many of these models consider homogeneous populations, thus failing to capture rich heterogeneities in terms of risk factors, vulnerabilities, economic participation, location, and social interactions. In this colloquium, Asuman Ozdaglar and Francesca Parese present networked SIR models that capture groups of agents with different characteristics and interaction patterns. They then discuss targeted dynamic interventions for testing and lockdown policies that minimize spread of infection while containing social and economic damage. Their focus is on dynamic time-varying policies that adaptively adjust as a function of a community’s infection level.

Asu Ozdaglar

Asuman Ozdaglar is MIT’s MathWorks Professor of Electrical Engineering and Computer Science, Department Head of the Electrical Engineering and Computer Science Department, and Deputy Dean of Academics at the Schwarzman College of Computing. She is affiliated with Laboratory for Information & Decision Systems and the Operations Research Center. Her research focuses on problems that arise in the analysis and optimization of large-scale dynamic multi-agent networked systems including communication networks, transportation networks, and social and economic networks.

Francesca Parise

Francesca Parise was named Assistant Professor of Electrical and Computer Engineering at Cornell University in July 2020. She previously served as a postdoctoral researcher at the Laboratory for Information and Decision Systems at MIT. She was recognized as an EECS rising star in 2017, and is the recipient of the Guglielmo Marin Award from the Istituto Veneto di Scienze, Lettere ed Arti, the SNSF Early Postdoc Fellowship, the SNSF Advanced Postdoc Fellowship, and the ETH Medal for her doctoral work.

August 20, 2020, 1 pm PT/4 pm ET

Lessons from COVID-19: Efficiency vs. Resilience

Moshe Y. Vardi, University Professor, Karen Ostrum George Distinguished Service Professor in Computational Engineering, Rice University

In both computer science and economics, efficiency is a cherished property. In computer science, the field of algorithms is almost solely focused on their efficiency. In economics, the main advantage of the free market is that it promises “economic efficiency.” A major lesson from COVID-19 is that both fields have over-emphasized efficiency and under-emphasized resilience. Professor Vardi argues that resilience is a more important property than efficiency and discusses how the two fields can broaden their focus to make resilience a primary consideration. He will include a technical example, showing how we can shift the focus in formal reasoning from efficiency to resilience.


Moshe Y. Vardi is a University Professor and the Karen Ostrum George Distinguished Service Professor in Computational Engineering at Rice University. He is the recipient of three IBM Outstanding Innovation Awards, the ACM SIGACT Goedel Prize, the ACM Kanellakis Award, the ACM SIGMOD Codd Award, the Blaise Pascal Medal, the IEEE Computer Society Goode Award, the EATCS Distinguished Achievements Award, the Southeastern Universities Research Association’s Distinguished Scientist Award, and the ACM SIGLOG Church Award. He is the author and co-author of over 600 papers and the books Reasoning about Knowledge and Finite Model Theory and Its Applications. He is a Fellow of the American Association for the Advancement of Science, the American Mathematical Society, the Association for Computing Machinery, the American Association for Artificial Intelligence, the European Association for Theoretical Computer Science, the Institute for Electrical and Electronic Engineers, and the Society for Industrial and Applied Mathematics. He is a member of the US National Academy of Engineering and National Academy of Science, the American Academy of Arts and Science, the European Academy of Science, and Academia Europaea. He holds six honorary doctorates. He is currently a Senior Editor of the Communications of the ACM, after having served for a decade as Editor-in-Chief.

August 13, 2020, 1 pm PT/4 pm ET

Predictive and Prescriptive Analytics for the COVID-19 Pandemic

Dimitris Bertsimas, Associate Dean of Business Analytics & Boeing Professor of Operations Research, MIT Sloan School of Management

The COVID-19 pandemic creates unprecedented challenges for healthcare providers and policymakers. How to triage patients when healthcare resources are limited? Whom to test? And how to design social distancing policies to contain the disease and its socioeconomic impact? Dimitris Bertsimas and Alexandre Jacquillat of MIT Sloan School of Management believe that analytics can provide an answer and have collected comprehensive data from hundreds of clinical studies, case counts, and hospital collaborations at This colloquium will present their epidemiological model of the disease’s dynamics, a machine-learning model of mortality risk, and a resource allocation model. Specifically, it will address: How can we predict admissions in intensive care units using machine learning? How does COVID-19 impact different demographic and socioeconomic populations? How does mobility impact the disease’s spread, and how to optimize social distancing policies? And how to augment COVID-19 tests with data-driven warnings that identify high-risk subjects? Bertsimas will present a new machine learning model for predicting being COVID-positive and mortality using data from over 40 hospitals around the world, along with high-performance computing (using the C3 AI suite), and advanced machine learning and artificial intelligence. He will summarize his research group’s end-to-end ML/AI methods, spanning epidemiological modeling (to model the disease’s spread), machine learning (to predict ICU admissions and test results), causal inference (to investigate disparities across populations), and optimal control (to support social distancing guidelines), as well as a new optimization model for allocating vaccines to minimize deaths.


Dimitris Bertsimas is currently the Boeing Professor of Operations Research and the Associate Dean of business Analytics at the Sloan School of Management at the Massachusetts Institute of Technology. His research interests include machine learning, optimization, and their applications in health care. He has co-authored more than 250 scientific papers and five graduate level textbooks. He is currently Editor in Chief of INFORMS Journal on Optimization and former Area Editor of Management Science in Optimization and of Operations Research in Financial Engineering. He has supervised 76 doctoral students and is currently supervising 25 others. He is a member of the National Academy of Engineering and he has received numerous research awards including the John von Neumann Theory Prize for fundamental contributions in Operations Research and Management Science and the INFORMS President Award for significant impact in society, both in 2019. Since March, 2020 he has led a group of 30 doctoral students, postdocs, and professors to study multiple aspects of COVID-19. These efforts are detailed at COVID Analytics. He has co-founded several companies over the years including Dynamic Ideas, a financial services company, sold to American Express in 2002, D2 Hawkeye,  sold to Verisk in 2009, Benefit Sciences, ReClaim, and Savvi Financial.

August 6, 2020, 1 pm PT/4 pm ET 

Optimal Targeted Lockdowns for COVID-19 in a Multi-Group SIR Model

Daron Acemoglu, Institute Professor Department of Economics, Massachusetts Institute of Technology

This colloquium will investigate targeted lockdowns using a multi-group SIR model, in which infection, hospitalization, and fatality rates vary among groups—in particular among young, middle-aged, and old patients. The model—developed by PI Daron Acemoglu with MIT Economics Professors Victor ChernozhukovIván Werning, and Michael Whinston—enables a tractable quantitative analysis of optimal policy. For baseline parameter values for the COVID-19 pandemic as applied to the United States, Daron Acemoglu and his colleagues find that optimal policies differentially targeting risk/age groups significantly outperform optimal uniform policies and most of the gains can be realized by having stricter lockdown policies on the oldest group. Intuitively, a strict and long lockdown for the most vulnerable group both reduces infections and enables less strict lockdowns for the lower risk groups. The colloquium also will investigate: the impacts of group distancing, testing, and contract tracing; the matching technology; and the expected arrival time of a vaccine for optimal policies. Overall, Acemoglu’s model indicates targeted policies combined with measures that reduce interactions among groups and increase testing and isolation of the infected can minimize both economic losses and deaths.

Daron Acemoglu

Daron Acemoglu is Institute Professor at MIT and an elected fellow of the National Academy of Sciences, the Turkish Academy of Sciences, the American Academy of Arts and Sciences, the Econometric Society, the European Economic Association, and the Society of Labor Economists. He is the author of five books, including Introduction to Modern Economic GrowthWhy Nations Fail: Power, Prosperity, and Poverty (joint with James A. Robinson), and The Narrow Corridor: States, Societies, and the Fate of Liberty (with James A. Robinson). His academic work covers a wide range of areas, including political economy, economic development, economic growth, inequality, labor economics and economics of networks. He has received the inaugural T. W. Shultz Prize from the University of Chicago in 2004, and the inaugural Sherwin Rosen Award for outstanding contribution to labor economics in 2004, Distinguished Science Award from the Turkish Sciences Association in 2006, the John von Neumann Award, Rajk College, Budapest in 2007, the Carnegie Fellowship in 2017, the Jean-Jacques Laffont Prize in 2018, and the Global Economy Prize in 2019.

July 30, 2020, 1 pm PT/4 pm ET

Networked Epidemiology Models for COVID-19 Analysis and Control

Tamer Bașar, the Swanlund Endowed Chair and CAS Professor of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign; Carolyn Beck, Professor of Industrial and Enterprise Systems Engineering, University of Illinois at Urbana-Champaign; and Rebecca Smith, Associate Professor, Department of Pathobiology, University of Illinois College of Veterinary Medicine

Spread of epidemics over large populations has been an important research area for several centuries, studied by epidemiologists, statisticians, mathematicians, and more recently data scientists. Over the past eight months or so, the science of epidemics has accelerated at an exponential rate due to the global threat caused by COVID-19. In addition, for quite some time, mathematical models of epidemics have been developed to help predict spread and inform policy makers as to what types of containment measures might be effective.  In this lecture, Carolyn Beck, Tamer Bașar, and Rebecca Smith will introduce several mathematical models within a networking (graph-theoretic) framework and discuss their work as well as others’ in: analyzing stability (or instability) of the equilibrium states (endemic and disease-free equilibria); optimally determining curing rates (through antidote control techniques); optimally modifying the network structure so as to mitigate spread; and developing algorithms to assimilate real- time testing data into networked epidemiological models. The speakers will discuss the plans of their project team—also comprised of Prashant Mehta (PI) and Matthew West of the University of Illinois at Urbana-Champaign and Philip E. Paré of Purdue University—in the development of models, algorithms, and software tools to support the state-level PCR (polymerase chain reaction) and serological testing efforts.

Tamer Basar, professor, electrical & computer engineering.

Tamer Başar has been with the University of Illinois at Urbana-Champaign since 1981, where he holds the Swanlund Endowed Chair, CAS Professor of Electrical and Computer Engineering, Professor at Coordinated Science Laboratory and Information Trust Institute, and Affiliate Professor, Mechanical Science and Engineering. He is also Director of the Center for Advanced Study. He is a member of the NAE, and Fellow of IEEE, IFAC, and SIAM. He has received several awards and recognitions over the years, including the highest awards of IEEE CSS, IFAC, AACC, and ISDG, the IEEE Control Systems Technical Field Award, and a number of international honorary doctorates and professorships. He has over 900 publications in systems, control, communications, optimization, and dynamic games, including six books. His current research interests include stochastic teams, games, and networks; multi-agent systems and learning; data-driven distributed optimization; spread of information and epidemics; security and trust; energy systems; and cyber-physical systems.

Carolyn L. Beck

Carolyn L Beck is a Professor at the University of Illinois at Urbana-Champaign in Industrial and Enterprise Systems Engineering, with affiliate appointments in Electrical and Computer Engineering, Mechanical Science and Engineering, and the Coordinated Science Lab. She currently serves on the Carle Illinois College of Medicine Admissions Committee. She has held visiting positions at KTH Royal Institute of Technology in Stockholm, Stanford University, and Lund University in Sweden. She has received national research awards, including the NSF CAREER Award and the ONR Young Investigator Award as well as local teaching awards. Her main research interests lie in the study of modeling and analysis of networked control systems and include the development of model approximation methods, network inference and aggregation, and distributed optimization and control methods.

ACES Research Academy participant.

Rebecca L. Smith is an Associate Professor in the Department of Pathobiology at the University of Illinois College of Veterinary Medicine, the Carl R. Woese Institute for Genomic Biology, and the National Center for Supercomputing Applications. Her research focuses on the understanding and use of complex data, including longitudinal datasets and heterogeneous data collection, for prediction and modeling of infectious diseases. Her current research focuses on understanding the impact of data collection on propagation of errors and uncertainty through prediction.

July 23, 2020, 1 pm PT/4 pm ET

Can Targeted Closures Reduce Economic Loss and Control COVID-19 Spread?

John Birge, Hobart W. Williams Distinguished Service Professor of Operations Management, University of Chicago Booth School of Business

In New York City, could the use of available data on individuals’ movements, the level of economic activity in different neighborhoods, and knowledge about the epidemic lead to decisions that control COVID-19 and substantially lower economic losses than citywide closures? Could targeted closures work? John Birge with his research colleagues Ozan Candogan of University of Chicago and Yiding Feng of Northwestern University are developing a spatial epidemic spread model for multiple New York City neighborhoods, whose residents fall into five COVID-19 related categories: 1) susceptible, 2) exposed, 3) infected clinical, 4) infected subclinical, and 5) recovered. Putting themselves in the position of city planners who seek a framework for policies that induce the lowest economic costs, Birge, Candogan, and Feng focus on areas with small and large numbers of infections, commuting patterns across them, and how infections in one neighborhood can trigger infections in others. The research team’s initial results indicate that targeted closures can achieve the same policy goals for disease prevention at substantially lower economic losses. In addition, they find that coordination with neighboring counties is paramount. Contrary to what might be expected, and due to the spatial aspect of the epidemic spread, they argue that New York City neighborhoods with higher levels of infections should not necessarily be the ones exposed to the most stringent economic closure measures.

Booth's John Birge, September 6, 2016. (Photo by Jean Lachat)

John Birge is the Hobart W. Williams Distinguished Service Professor of Operations Management at the University of Chicago Booth School of Business. He studies mathematical modeling of systems under uncertainty with applications in energy, finance, health care, manufacturing, public policy, and transportation. He is an INFORMS Fellow, MSOM Society Distinguished Fellow, member of the US National Academy of Engineering, and Editor-in-Chief of Operations Research. He is also former dean of engineering at Northwestern University, professor and chair of industrial and operations engineering at the University of Michigan, and holds a bachelor’s degree in mathematics from Princeton University and a master’s and Ph.D. in operations research from Stanford University.

July 16, 2020, 1 pm PT/4 pm ET

Using AI Techniques for Detection and Containment of COVID-19 and Emerging Diseases

Alberto Sangiovanni-Vincentelli, Edgar L. and Harold H. Buttner Chair of Electrical Engineering and Computer Science, UC Berkeley

When using AI methods to tackle the COVID-19 pandemic, distribution shifts from test data to training data create challenges. These shifts often lead to degraded performance, presenting challenges when deploying machine-learning models in healthcare AI and autonomous driving applications. In the first part of this talk, Professor Sangiovanni-Vincentelli will review the risks brought by incipient diseases and domain mismatch–two notable types of distribution shifts–to high-stake decision-making scenarios. To address the challenges, his research team has devised approaches that leverage the uncertainty information from ensemble learners and domain randomization. Their theoretical and empirical results show that these approaches produce classifiers that are more robust against distribution shifts. For COVID-19 research, the sparsity of emerging disease data, especially at the initial outbreak of the epidemic, represents another challenge in using AI to detect and contain disease spread. In the second part of the talk, Professor Sangiovanni-Vincentelli will present his research team’s plan for tackling this challenge by building upon the above-mentioned techniques and incorporating them into state-of-the-art, human-AI collaborative methods. This is a joint investigation with Geoff Tison of UCSF and Yuxin Chen of the University of Chicago.


Alberto Sangiovanni-Vincentelli is the Edgar L. and Harold H. Buttner Chair of Electrical Engineering and Computer Science at University of California, Berkeley, where he has served on faculty since 1975. He is Special Advisor to the Dean of Engineering for Entrepreneurship and Chair of the Faculty Advisors to Berkeley’s accelerator, SkyDeck. His many honors include the IEEE-EDAA Kaufman Award for pioneering contributions to electronic design automation (EDA) and the IEEE/RSE Maxwell Medal for groundbreaking contributions that have had an exceptional impact on the development of electronics and electrical engineering or related fields.” He co-founded Cadence and Synopsys, two leading EDA companies with combined NASDAQ valuation of close to $60 billion. He is a board member of Cadence, KPIT, ISEO, ExpertSystem, Cogisen, Cy4gate; has consulted for companies worldwide, including Intel, IBM, ST, Mercedes, BMW, UTC, GM; and is International Advisory Council Chair of the Milano Innovation District. He is a member of the NAE, a IEEE and ACM Fellow, and holds an Honorary Doctorate from Aalborg University and KTH. He has published over 1,000 papers and 19 books with an h-index of 117 (Google Scholar) and graduated over 100 doctorate students.

July 9, 2020, 1 pm PT/4 pm ET 

Translating AI Research in Breast Cancer Imaging to COVID-19

Maryellen Giger, A.N. Pritzker Professor of Radiology at The University of Chicago

The COVID-19 pandemic presents a pressing public health need for computational techniques to augment the interpretation of medical images in their role for: surveillance and early detection of COVID-19 resurgence via monitoring of medical imaging data; detection, triaging, and differential diagnosis of COVID-19 patients; and prognosis, including prediction and monitoring of response, for use in patient management. While thoracic imaging, including chest radiography and computed tomography, are being re-examined for their role in patient management, the limitations for improved interpretation are partially due to the qualitative interpretation of the images. Professor Giger and her colleagues at University of Chicago and Argonne National Laboratory aim to develop machine intelligence methods to aid in the interrogation of medical images from COVID-19 patients. They draw on decades of AI development of medical images to quantify and explain the COVID-19 presentation on imaging, specifically through machine learning methods of interrogating cancer on multimodality breast images for “virtual biopsies.”

Maryellen Giger

Maryellen L. Giger is the A.N. Pritzker Professor of Radiology and Medical Physics at the University of Chicago. For decades, she has worked on computer-aided diagnosis/machine learning/deep learning in medical imaging and cancer diagnosis and management. Her AI research in breast cancer for risk assessment, diagnosis, prognosis, and therapeutic response has yielded various translated components, and she is using these “virtual biopsies” in imaging-genomics association studies. Giger is a former president of AAPM and of SPIE, and is the Editor-in-Chief of the Journal of Medical Imaging. She is a member of the National Academy of Engineering; Fellow of AAPM, AIMBE, SPIE, SBMR, IEEE, and IAMBE; and was cofounder, equity holder, and scientific advisor of Quantitative Insights (now Qlarity Imaging), which produces QuantX, the first FDA-cleared, machine-learning driven CADx system.