About

Yale's Institute for Foundations of Data Science (FDS) also known as the Kline Tower Institute, was created to advance research in the mathematical, algorithmic, and statistical foundations of data science and their application to other disciplines. The institute integrates faculty from departments and schools across the university to help scholars apply new methods of data science to their research. In turn, exposure to the unmet needs of domain scientists inspires advances in foundational research.

The institute will hold its activities at varying venues around campus. In August 2023, FDS will move into Kline Tower and provide a venue for data scientists to meet, learn about recent advances, discover exciting problems, host visitors, and hold seminars, workshops, and conferences.

Institute for Foundations of Data Science
Seminar Series

Wednesday 2 November 2022, 4pm
Analyzing the National Football League is challenging, but player tracking data is here to help
DL220
10 Hillhouse Avenue
New Haven, CT
Michael Lopez Sr.
Director of Football Data/Analytics National Football League
Abstract

Most historical National Football League (NFL) analysis, both mainstream and academic, has relied on play-by-play data to generate team and player-level trends. Given the number of outside variables that impact on-field results, such as play call and game situation, findings are often no more than interesting anecdotes. With the release of player tracking data, however, analysts can appropriately ask and answer questions that better isolate player skill and coaching strategy. In this talk, we highlight the limitations of traditional analyses, and use a decades-old punching bag for analysts – fourth-down strategy – as a microcosm for why tracking data is needed.

Wednesday 9 November 2022, 4pm
Exploring Robustness and Energy-Efficiency in Neural Systems with Spike-based Machine Intelligence
DL220
10 Hillhouse Avenue
New Haven, CT
Priya Panda
Assistant Professor, Electrical Engineering, Yale University
Abstract

Spiking Neural Networks (SNNs) have recently emerged as an alternative to deep learning due to their huge energy efficiency benefits on neuromorphic hardware. In this presentation, I will talk about important techniques for training SNNs which bring a huge benefit in terms of latency, accuracy, interpretability, and robustness. We will first delve into how training is performed in SNNs. Training SNNs with surrogate gradients presents computational benefits due to short latency. However, due to the non-differentiable nature of spiking neurons, the training becomes problematic and surrogate methods have thus been limited to shallow networks. To address this training issue with surrogate gradients, we will go over a recently proposed method Batch Normalization Through Time (BNTT) that allows us to train SNNs from scratch with very low latency and enables us to target interesting applications like video segmentation and beyond traditional learning scenarios, like federated training. Another critical limitation of SNNs is the lack of interpretability. While a considerable amount of attention has been given to optimizing SNNs, the development of explainability still is at its infancy. I will talk about our recent work on a bio-plausible visualization tool for SNNs, called Spike Activation Map (SAM) compatible with BNTT training. The proposed SAM highlights spikes having short inter-spike interval, containing discriminative information for classification. Finally, with proposed BNTT and SAM, I will highlight the robustness aspect of SNNs with respect to adversarial attacks. In the end, I will talk about interesting prospects of SNNs for non-conventional learning scenarios such as privacy-preserving distributed learning as well as unraveling the temporal correlation in SNNs with feedback connections. Finally, time permitting, I will talk about the prospects of SNNs for novel and emerging compute-in-memory hardware that can potentially yield order of magnitude lower power consumption than conventional CPUs/GPUs.

People

Leadership

Dan Spielman headshot
Dan Spielman
Director
Tom Keegan headshot
Tom Keegan
Managing Director
Emily Hau headshot
Emily Hau
Associate Director

Members

Dirk Bergemann headshot
Dirk Bergemann
Douglass and Marion Campbell Professor of Economics
Claire Bowern headshot
Claire Bowern
Professor of Linguistics; Director of Undergraduate Studies
Elisa Celis headshot
Elisa Celis
Assistant Professor of Statistics & Data Science
Joseph Chang headshot
Joseph Chang
James A. Attwood Professor of Statistics and Data Science
Xiaohong Chen headshot
Xiaohong Chen
Malcolm K. Brachman Professor of Economics
Nicholas Christakis headshot
Nicholas Christakis
Sterling Professor of Social and Natural Science
Alex Coppock headshot
Alex Coppock
Associate Professor (on term) of Political Science
Forrest Crawford headshot
Forrest Crawford
Associate Professor of Biostatistics, Statistics & Data Science, Ecology & Evolutionary Biology, and Management
Jun Deng headshot
Jun Deng
Professor of Therapeutic Radiology; Director of Physics Research, Therapeutic Radiology
James Duncan headshot
James Duncan
Ebenezer K. Hunt Professor and Chair, Department of Biomedical Engineering
David van Dijk headshot
David van Dijk
Assistant Professor of Medicine & Computer Science
John W. Emerson headshot
John W. Emerson
Professor Adjunct and Director of Graduate Studies in the Department of Statistics & Data Science
Emily Erikson headshot
Emily Erikson
Professor and Director of the Fox International Fellowship Program
Zhou Fan headshot
Zhou Fan
Assistant Professor of Statistics and Data Science
Alan Gerber headshot
Alan Gerber
Sterling Professor, Department of Political Science
Mark Gerstein headshot
Mark Gerstein
Williams Professor of Biomedical Informatics
Soheil Ghili headshot
Soheil Ghili
Assistant Professor, School of Management
Amy Justice headshot
Amy Justice
CNH Long Professor of Medicine and Public Health
Joshua Kalla headshot
Joshua Kalla
Assistant Professor of Political Science
Dionysis Kalogerias headshot
Dionysis Kalogerias
Assistant Professor of Electrical Engineering
Michael J. Kane headshot
Michael J. Kane
Assistant Professor of Biostatistics
Ed Kaplan headshot
Ed Kaplan
William N and Marie A Beach Professor of Operations Research
Amin Karbasi headshot
Amin Karbasi
Associate Professor, Electrical Engineering, Computer Science, Statistics and Data Science
Rohan Khera headshot
Rohan Khera
Assistant Professor of Medicine
Steven H. Kleinstein headshot
Steven H. Kleinstein
Anthony N. Brady Professor of Pathology, Co-Director, Program in Computational Biology & Bioinformatics
Smita Krishnaswamy headshot
Smita Krishnaswamy
Associate Professor, Computer Science
Harlan M. Krumholz headshot
Harlan M. Krumholz
Harold H. Hines, Jr. Professor of Medicine (Cardiology)
John D. Lafferty headshot
John D. Lafferty
John C. Malone Professor of Statistics and Data Science
Gregory Laughlin headshot
Gregory Laughlin
Professor of Astronomy
Roy R. Lederman headshot
Roy R. Lederman
Assistant Professor of Political Science
Brian Macdonald headshot
Brian Macdonald
Senior Lecturer and Research Scientist, Department of Statistics and Data Science
Vahideh Manshadi headshot
Vahideh Manshadi
Associate Professor of Operations, Yale School of Management
Ethan Meyers headshot
Ethan Meyers
Visiting Associate Professor of Statistics and Data Science
Priyadarshini Panda headshot
Priyadarshini Panda
Assistant Professor of Electrical Engineering
Dragomir Radev headshot
Dragomir Radev
A. Bartlett Giamatti Professor of Computer Science
Jonathan Reuning-Scherer headshot
Jonathan Reuning-Scherer
Senior Lecturer in Statistics and Data Science
Luke C. Sanford headshot
Luke C. Sanford
Assistant Professor of Environmental Policy and Governance
Fredrik Sävje headshot
Fredrik Sävje
Assistant Professor, Department of Political Science
Jasjeet Sekhon headshot
Jasjeet Sekhon
Eugene Meyer Professor of Political Science and of Statistics ∓ Data Science
Jason A. Shaw headshot
Jason A. Shaw
Associate Professor of Linguistics
Daniel A. Spielman headshot
Daniel A. Spielman
Sterling Professor of Computer Science, Professor Statistics and Data Science and of Mathematics
John Tsang headshot
John Tsang
Professor, Department of Immunobiology
Nisheeth Vishnoi headshot
Nisheeth Vishnoi
A. Bartlett Giamatti Professor of Computer Science
Van Vu headshot
Van Vu
Percy F. Smith Professor of Mathematics and Professor of Data Science
Andre Wibisono headshot
Andre Wibisono
Assistant Professor of Computer Science
Yihong Wu headshot
Yihong Wu
Professor, Department of Statistics and Data Science
Zhuoran Yang headshot
Zhuoran Yang
Professor of Statistics and Data Science
Ilker Yildirim headshot
Ilker Yildirim
Assistant Professor of Psychology
Rex Ying headshot
Rex Ying
Assistant Professor, Department of Computer Science
Harrison Zhou headshot
Harrison Zhou
Henry Ford II Professor, Department of Statistics and Data Science
Hongyu Zhao headshot
Hongyu Zhao
Professor of Biostatistics, Professor of Genetics
Steven Zucker headshot
Steven Zucker
David and Lucile Packard Professor

Join Us

To sign up to receive announcements of future talks in this series and other events being run by FDS

Subscribe Here

Apply for a Postdoctoral Position

Yale’s Institute for Foundations of Data Science (FDS) is seeking applications for postdoctoral positions in Data Science. These will be generously supported postdoctoral positions, expected to last 2-3 years, for independent scholars working on the foundations of data science. FDS postdocs can select multiple mentors from among the members of the institute, and can change their mentors during their fellowship. This is an opportunity to work with leading theorists as well as domain scientists who are eager to collaborate. A list of the members may be found on this site. Yale’s Data Science Initiative has supported the rapid growth of the departments of Statistics & Data Science and Computer Science, as well as many interdisciplinary activities in which the postdocs could participate, including a Data Intensive Social Science Center, a center for Biomedical Data Science, and the Schmidt Program on Artificial Intelligence, Emerging Technologies, and National Power.

Apply Here

Apply to be a Member

Members of FDS come from departments and schools across the university, united by a research interest in the foundations of data science. Member applicants with appointments in FAS or SEAS should be ladder faculty, hold teaching positions, or be research scientists. Members from other schools should have appointments that allow graduate advising. Reasonable exceptions to this policy are possible. We will review applications submitted by any member of the Yale faculty, but note we have a phased approach to membership to grow our numbers in line with our capacity. To ensure our ability to scale appropriately, we hope you understand if we defer a decision on your membership to a later date.

Apply for Membership