Skip to main content

Lytle Lecture Series

The Dean W. Lytle Electrical & Computer Engineering Endowed Lecture Series is the Department’s premier annual event, featuring internationally renowned researchers in the field of communications, signal processing, control systems and machine learning.

The lectureship is made possible by an endowment established in 2006, the centennial year of the Department, through fundraising efforts led by Louis Scharf, a doctoral student of Dean’s, in collaboration with Dean’s wife, Marilyn Lytle, and support from the Lytle family. Many members of the UW ECE community responded with generous donations to honor Dean Lytle, including his graduate students, his colleagues at Honeywell’s Marine Systems Center, as well as alumni and friends.

Lectures are free and open to the public.


2024-2025

Save the Date! October 17, 2024

More details coming soon!


Previous Lectures

2023-2024

2023-2024

Yann LeCun

Yann LeCun

VP and Chief AI Scientist, Meta, and Professor, NYU

Wednesday, January 24, 2024


Yann LeCun is VP and Chief AI Scientist at Meta and Silver Professor at NYU affiliated with the Courant Institute, the Center for Data Science, the Center for Neural Science and the Electrical and Computer Engineering Department. He was the founding Director of Facebook AI Research and of the NYU Center for Data Science. 

He received the Electrical Engineer Diploma from ESIEE, Paris (1983), and a PhD in CS from Sorbonne Université (1987). After a postdoc at the University of Toronto, he joined AT&T Bell Laboratories (Holmdel, NJ) in 1988, later becoming the head of the Image Processing Research Department at AT&T Labs-Research in 1996. He joined NYU as a professor in 2003, following a brief period at the NEC Research Institute (Princeton). In 2012. He became the founding director of the NYU Center for Data Science. In late 2013, he was named Director of AI Research at Facebook, remaining on the NYU faculty part-time. He held a visiting professor chair at Collège de France in 2015-2016.

His current interests include AI, machine learning, computer perception, robotics, and computational neuroscience.  He is best known for his contributions to deep learning and neural networks, particularly the convolutional network model which is very widely used in computer vision and speech recognition applications.  He has published over 200 papers on these topics as well as on handwriting recognition, image compression, and dedicated hardware for AI. 

LeCun is founder and general co-chair of ICLR and has served on several editorial boards and conference organizing committees. He is co-chair of the program Learning in Machines and Brains of the Canadian Institute for Advanced Research. He has been on the science advisory board of IPAM (since 2008) and the board of trustees of ICERM . He has advised many companies and co-founded startups Elements Inc. and Museami. He is in the New Jersey Inventor Hall of Fame. He is a member of the US National Academy of Sciences, the National Academy of Engineering, and the French Académie des Sciences. He is a Chevalier de la Légion d’Honneur, a fellow of AAAI and AAAS, the recipient of the 2022 Princess of Asturias Award, the 2014 IEEE Neural Network Pioneer Award, the 2015 IEEE PAMI Distinguished Researcher Award, the 2016 Lovie Lifetime Achievement Award, the 2018 University of Pennsylvania Pender Award, and honorary doctorates from IPN, Mexico, EPFL and Université Côte d’Azur.

He is the recipient of the 2018 ACM Turing Award (with Geoffrey Hinton and Yoshua Bengio) for “conceptual and engineering breakthroughs that have made deep neural networks a critical component of computing”.

Lytle Lecture

Objective-Driven AI: Towards Machines that can Learn, Reason, and Plan

Abstract

How could machines learn as efficiently as humans and animals? How could machines learn how the world works and acquire common sense? How could machines learn to reason and plan? Current AI architectures, such as Auto-Regressive Large Language Models, fall short.  I will propose a modular cognitive architecture that may constitute a path towards answering these questions.  The centerpiece of the architecture is a predictive world model that allows the system to predict the consequences of its actions and to plan a sequence of actions that optimize a set of objectives.  The objectives include guardrails that guarantee the system’s controllability and safety.  The world model employs a Hierarchical Joint Embedding Predictive Architecture (H-JEPA) trained with self-supervised learning.  The JEPA learns abstract representations of the percepts that are simultaneously maximally informative and maximally predictable.  The corresponding working paper is available here.

2022-2023

Anca Dragan

Anca Dragan, associate professor in the EECS Department at UC Berkeley

Monday, November 14, 2022

Anca Dragan is an associate professor in the EECS Department at UC Berkeley. Her goal is to enable robots (and AI agents more broadly) to work for and around people. She runs the InterACT laboratory, where she focuses on algorithmic human-robot interaction: algorithms that move beyond the robot’s function in isolation and generate robot behavior that coordinates well with human actions and is aligned with what humans actually want the robot to do. Anca received her Ph.D. from Carnegie Mellon University’s Robotics Institute. She helped found the Berkeley AI Research Laboratory, and is co-principal investigator of the Center for Human-Compatible AI. She has been honored by the Presidential Early Career Award for Scientists and Engineers (PECASE), NSF CAREER, Sloan, Okawa, ONR Young Investigator Award, MIT TR35, and the IEEE RAS Early Academic Career Award.

Lytle Lecture: Robotics algorithms that take people into account

Abstract

I discovered AI by reading “Artificial Intelligence: A Modern Approach”. What drew me in was the concept that you could specify a goal or objective for a robot, and it would be able to figure out on its own how to sequence actions in order to achieve it. In other words, we don’t have to hand-engineer the robot’s behavior — it emerges from optimal decision making. Throughout my career in robotics and AI, it has always felt satisfying when the robot would autonomously generate a strategy that I felt was the right way to solve the task, and it was even better when the optimal solution would take me a bit by surprise. In “Intro to AI” I share with students an example of this, where a mobile robot figures out it can avoid getting stuck in a pit by moving along the edge. In my group’s research, we tackle the problem of enabling robots to coordinate with and assist people: for example, autonomous cars driving among pedestrians and human-driven vehicles, or robot arms helping people with motor impairments (together with UCSF Neurology). And time and time again, what has sparked the most joy for me is when robots figure out their own strategies that lead to good interaction — when we don’t have to hand-engineer that an autonomous car should inch forward at a 4-way stop to assert its turn, for instance, but instead, the behavior emerges from optimal decision making. In this talk, I want to share how we’ve set up optimal decision making problems that require the robot to account for the people it is interacting with, and the surprising strategies that have emerged from that along the way. And I am very proud to say that you can also read a bit about these aspects now in the 4th edition of “Artificial Intelligence: A Modern Approach”, where I had the opportunity to edit the robotics chapter to include optimization and interaction.

2021-2022

Muriel Médard, Cecil H. and Ida Green Professor in the Electrical Engineering and Computer Science (EECS) Department at MIT

Muriel Médard

Monday, October 18, 2021

Lytle Lecture, 12 to 1:30 p.m.: “Deviation from the standard — toward opening up 5G telecommunications”

Technical Seminar, 2 to 3 p.m.: Guessing Random Additive Noise Decoding (GRAND)”

Muriel Médard Abstracts and Bio

2020-2021

Scott AaronsonProfessor, University of Texas at Austin; Director, Quantum Information Center at UT Austin

Thursday, November 19, 2020

Lytle Lecture, 3:30 to 5:00 p.m: “Quantum Computational Supremacy and Its Applications”

Quantum Panel, 10:30 a.m. to 12:00 p.m: “Panel Discussion on Quantum Computing Research”

Kai-Mei Fu (UW ECE and UW Physics professor, UW QuantumX) and industry experts Brent VanDevender, (Pacific Northwest National Laboratory), David Bacon, (IonQ), and Krysta Svore (Microsoft).

2019-2020

Stéphane Mallat Applied Mathematician, Distinguished Research Scientist, Collège de France, Paris; Flatiron Institute, New York

Colloquium Series Lecture:

Tuesday, Dec. 3, 10:30 to 11:30 a.m., ECE 105: “Interpretable Deep Networks for Classification, Generation and Physics

Lytle Lecture:

Tuesday, Dec. 3, 3:30 to 5:30 p.m. (doors open at 3:00 p.m.), Paul G. Allen Center Atrium: “Mathematical Mysteries of Deep Neural Networks

2018-2019

Claire Tomlin

Claire Tomlin Charles A. Desoer Chair in the College of Engineering, professor in electrical engineering and computer science, University of California Berkeley.

Monday, Nov. 5, 3:30 to 4:30 p.m., HUB Lyceum: “Safe learning in robotics”
Tuesday, Nov. 6, 10:30 to 11:30 a.m., EEB 105: “Towards real-time reachability”

Safe Learning in Robotics

Towards Real-Time Reachability

2017-2018

Robert W. Heath Jr.Cullen Trust for Higher Education Endowed Professor in the Department of Electrical and Computer Engineering, University of Texas, Austin

Millimeter Wave Communication: From Origins to Disruptive Applications

Millimeter Wave communication using out-of-band information

2016-2017

David DonohoAnne T. and Robert M. Bass Professor of Humanities and Sciences; Professor of Statistics, Stanford University

Compressed Sensing: From Theory to Practice

High-dimensional statistics in light of the spiked covariance model

2015-2016

David TseProfessor of Electrical Engineering, Stanford University

The Science of Information: From Pushing Bits Over the Air to Assembling World’s Largest Jigsaw Puzzles

Haplotype Phasing, Convolutional Codes and Community Detection

2014-2015

Arogyaswami PaulrajEmeritus Professor, Stanford University

Evolution of Mobile Air Interface Technology

Road to 5G

2013-2014

Stephen P. BoydSamsung Professor of Engineering and Professor of Electrical Engineering, Stanford University

The Science of Better: Embedded Optimization in Smart Systems

Convex Optimization: From Embedded Real-time to Large-Scale Distributed

2012-2013

Alan S. WillskyEdwin Sibley Webster Professor of Electrical Engineering and Computer Science and Director of the Laboratory for Information and Decision Systems at Massachusetts Institute of Technology

Building a Career on the Kindness of Others

Learning & Inference for Graphical & Hierarchical Models: A Personal Journey

2011-2012

Ingrid DaubechiesJames B. Duke Professor of Mathematics, Duke University

Can Image Analysis Detect the Hand of the Master? Wavelets and Applications to the Analysis of Art Paintings

Quantifying the (dis)similarity Between Surfaces

2010-2011

Thomas KailathHitachi America Professor of Engineering, Emeritus, Stanford University

From Radiative Transfer Theory to Fast Algorithms for Cell Phones | Technical Colloquium

2009-2010

Irwin JacobsCo-founder, Qualcomm

From Cell Phones to Smart Phones to Smart Books — An Exciting Journey

2008-2009

Vince Poor

Vince PoorDean of the School of Engineering & Applied Sciences at Princeton University

Competition and Collaboration in Wireless Networks