Select a calendar:
Filter March Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for March 20, 2023
-
ECE-S Seminar - Dr Shiry Ginosar
Mon, Mar 20, 2023 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr Shiry Ginosar, Postdoctoral Fellow | University of California, Berkeley
Talk Title: Toward Artificial Social Intelligence
Abstract: As the covid pandemic made abundantly clear-”multi-faceted, face-to-face interaction is the most effective form of communication-”much more so than written text messages or phone calls. And yet, most current AI efforts focus primarily on text systems. In my work, I try to push the limits of machine perception systems toward artificially intelligent agents that can perceive and model the rich, multimodal signals of face-to-face human social interaction: speech and communicative gesture. I will cover several projects that take steps in this direction in the one-to-many scenario of lectures and monologues and one-on-one dyadic face-to-face communication. Through these examples, I will argue that it is possible to model minute, indescribable visual and auditory details of multi-faceted human communication using data-driven methods without relying on annotation. I will then broaden the discussion to questions in social intelligence, such as body language, abstract communicative motion, and spatiotemporal trends of social norms, and suggest directions for future inquiries.
Biography: Shiry Ginosar is a Computing Innovation Postdoctoral Fellow at UC Berkeley, advised by Jitendra Malik. She completed her Ph.D. in Computer Science at UC Berkeley, under the supervision of Alyosha Efros. Prior to joining the Computer Vision group, she was part of Bjoern Hartmann's Human-Computer Interaction lab at Berkeley. Earlier in her career, she was a Visiting Scholar at the CS Department of Carnegie Mellon University, with Luis von Ahn and Manuel Blum in the field of Human Computation. Between her academic roles, she spent four years at Endeca as a Senior Software Engineer. In her distant past, Shiry trained fighter pilots in F-4 Phantom flight simulators as a Staff Sergeant in the Israeli Air Force. Shiry's research has been covered by The New Yorker, The Wall Street Journal, and the Washington Post, amongst others. Her work has been featured on PBS NOVA, exhibited at the Israeli Design Museum and is part of the permanent collection of the Deutsches Museum. Her patent-pending research work inspired the founding of a startup. Shiry has been named a Rising Star in EECS, and is a recipient of the NSF Graduate Research Fellowship, the California Legislature Grant for graduate studies, and the Samuel Silver Memorial Scholarship Award for combining intellectual achievement in science and engineering with serious humanistic and cultural interests.
Host: Dr Antonio Ortega, aortega@usc.edu
Webcast: https://usc.zoom.us/j/93935933525?pwd=cVVWd2JoQzBhcXZuWDAzalp3eEZYUT09More Information: ECE Seminar Announcement 03.20.2023 - Shiry Ginosar.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 248
WebCast Link: https://usc.zoom.us/j/93935933525?pwd=cVVWd2JoQzBhcXZuWDAzalp3eEZYUT09
Audiences: Everyone Is Invited
Contact: Miki Arlen
-
CS Colloquium: Rika Antonova (Stanford University) - Enabling Self-sufficient Robot Learning
Mon, Mar 20, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Rika Antonova, Stanford University
Talk Title: Enabling Self-sufficient Robot Learning
Series: CS Colloquium
Abstract: Autonomous exploration and data-efficient learning are important ingredients for helping machine learning handle the complexity and variety of real-world interactions. In this talk, I will describe methods that provide these ingredients and serve as building blocks for enabling self-sufficient robot learning.
First, I will outline a family of methods that facilitate active global exploration. Specifically, they enable ultra data-efficient Bayesian optimization in reality by leveraging experience from simulation to shape the space of decisions. In robotics, these methods enable success with a budget of only 10-20 real robot trials for a range of tasks: bipedal and hexapod walking, task-oriented grasping, and nonprehensile manipulation.
Next, I will describe how to bring simulations closer to reality. This is especially important for scenarios with highly deformable objects, where simulation parameters influence the dynamics in unintuitive ways. The success here hinges on finding a good representation for the state of deformables. I will describe adaptive distribution embeddings that provide an effective way to incorporate noisy state observations into modern Bayesian tools for simulation parameter inference. This novel representation ensures success in estimating posterior distributions over simulation parameters, such as elasticity, friction, and scale, even for scenarios with highly deformable objects and using only a small set of real-world trajectories.
Lastly, I will share a vision of using distribution embeddings to make the space of stochastic policies in reinforcement learning suitable for global optimization. This research direction involves formalizing and learning novel distance metrics on this space and will support principled ways of seeking diverse behaviors. This can unlock truly autonomous learning, where learning agents have incentives to explore, build useful internal representations and discover a variety of effective ways of interacting with the world.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Rika is a postdoctoral scholar at Stanford University and a recipient of the NSF/CRA Computing Innovation Fellowship for research on active learning of transferable priors, kernels, and latent representations for robotics. Rika completed her Ph.D. work on data-efficient simulation-to-reality transfer at KTH. Earlier, she obtained a research Master's degree from the Robotics Institute at Carnegie Mellon University, where she developed Bayesian optimization methods for robotics and for personalized tutoring systems. Before that, Rika was a software engineer at Google, first in the Search Personalization group and then in the Character Recognition team (developing open-source OCR engine Tesseract).
Host: Jesse Thomason
Location: Ronald Tutor Hall of Engineering (RTH) - 115
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
PHD Thesis Defense - Dimitris Stripelis
Mon, Mar 20, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
University Calendar
PHD Thesis Defense - Dimitris Stripelis
Title:
Heterogeneous Federated Learning
Committee Members:
Jose-Luis Ambite (Chair), Cyrus Shahabi, Paul Thompson, Greg Ver Steeg
Abstract:
Data relevant to machine learning problems are distributed across multiple data silos that cannot share their data due to regulatory, competitiveness, or privacy reasons. Federated Learning has emerged as a standard computational paradigm for distributed training of machine learning and deep learning models across silos. However, the participating silos may have heterogeneous system capabilities and data specifications. In this thesis, we address the challenges in federated learning arising from both computational and semantic heterogeneities. We present federated training policies that accelerate the convergence of the federated model and lead to reduced communication, processing, and energy costs during model aggregation, training, and inference. We show the efficacy of these policies across a wide range of challenging federated environments with highly diverse data distributions in benchmark domains and in neuroimaging. We conclude by describing the federated data harmonization problem and presenting a comprehensive federated learning and integration system architecture that addresses the critical challenges of secure and private federated data harmonization, including schema mapping, data normalization, and data imputation.
Location: https://usc.zoom.us/j/93599773555?pwd=TmI3M1JvTkxEV05DSmQ3dzYyVElmQT09
Audiences: Everyone Is Invited
Contact: Asiroh Cham
Event Link: https://usc.zoom.us/j/93599773555?pwd=TmI3M1JvTkxEV05DSmQ3dzYyVElmQT09
-
AME Seminar
Mon, Mar 20, 2023 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Weiyu Li, Stanford
Talk Title: Battery Avatar: First-Principles Modeling and Data Analytics
Abstract: Rechargeable lithium batteries are electrochemical devices that are widely used in portable electronics and electric-powered vehicles. A breakthrough in battery performance requires advancements in battery cell configurations at the microscale level. This, in turn, places a premium on the ability to accurately predict complex multiphase thermoelectrochemical phenomena, e.g., migration of ions interacting with composite porous materials that constitute a battery cell microstructure. Optimal design of porous cathodes requires efficient quantitative models of microscopic (pore-scale) electrochemical processes and their impact on battery performance. In this talk, I will discuss effective properties (electrical conductivity, ionic diffusivity, reaction parameters) of a composite electrode comprising the active material coated with a mixture of the binder and conductor (the carbon binder domain or CBD). When used to parameterize the industry-standard pseudo-twodimensional (P2D) models, they significantly improve the predictions of lithiation curves in the presence of CBD. On the lithium anode, dendritic growth is a leading cause of degradation and catastrophic failure of lithium-metal batteries. Deep understanding of this phenomenon would facilitate the design of strategies to reduce, or completely suppress, the instabilities characterizing electrodeposition on the lithium anode. This would improve the safety of lithium-metal batteries with liquid electrolyte and all-solid-state lithium batteries. I will present the results of our analysis, which indicate that the use of anisotropic electrolytes and buffer layers can suppress dendritic growth of lithium metal.
Biography: Weiyu Li has received her M.Sc. degree in Mechanical and Aerospace Engineering from Princeton University and is scheduled to obtain her PhD in Energy Science and Engineering from Stanford University in the Spring of 2023. Her research focuses on modeling and simulation of electrochemical transport in energy storage systems, aiming to provide mechanistic insights into the optimal design of porous electrodes, electrolyte, etc. Her other research interests include data assimilation and biomedical modeling. Weiyu Li is the recipient of the Siebel Scholars Award in Energy Science, class of 2023, and of the Princeton University Fellowship in Natural Sciences and Engineering.
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Webcast: https://usc.zoom.us/j/95805178776?pwd=aEtTRnQ2MmJ6UWE4dk9UMG9GdENLQT09Location: Olin Hall of Engineering (OHE) - 406
WebCast Link: https://usc.zoom.us/j/95805178776?pwd=aEtTRnQ2MmJ6UWE4dk9UMG9GdENLQT09
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
