Events for the 3rd week of April
-
ECE-S Seminar - Dr Stephen Tu
Mon, Apr 10, 2023 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr Stephen Tu, Research Scientist at Google Brain (Robotics at Google)
Talk Title: The foundations of machine learning for feedback control
Abstract: Recent breakthroughs in machine learning offer unparalleled optimism for the future capabilities of artificial intelligence. However, despite impressive progress, modern machine learning methods still operate under the fundamental assumption that the data at test time is generated by the same distribution from which training examples are collected. In order to build robust intelligent systems-”self-driving vehicles, robotic assistants, smart grids-”which safely interact with and control the surrounding environment, one must reason about the feedback effects of models deployed in closed-loop.
In this talk, I will discuss my work on developing a principled understanding of learning-based feedback systems, grounded within the context of robotics. First, motivated by the fact that many real world systems naturally produce sequences of data with long-range dependencies, I will present recent progress on the fundamental problem of learning from temporally correlated data streams. I will show that in many situations, learning from correlated data can be as efficient as if the data were independent. I will then examine how incremental stability-”a core idea in classical control theory-”can be used to study feedback-induced distribution shift. In particular, I will characterize how an expert policy's stability properties affect the end-to- end sample complexity of imitation learning. I will conclude by showing how these insights lead to practical algorithms and data collection strategies for imitation learning.
Biography: Stephen Tu is a research scientist at Robotics at Google in New York City. His research interests are focused on a principled understanding of the effects of using machine learning models for feedback control, with specific emphasis on robotics applications. He received his Ph.D. from the University of California, Berkeley in EECS under the supervision of Ben Recht.
Host: Dr Mahdi Soltanolkotabi, soltanol@usc.edu
Webcast: https://usc.zoom.us/j/92463220973?pwd=UHJEVmZFV2V2L25zOUo1aDY0cTFNQT09More Information: ECE Seminar Announcement 04.10.2023 Stephen Tu.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 248
WebCast Link: https://usc.zoom.us/j/92463220973?pwd=UHJEVmZFV2V2L25zOUo1aDY0cTFNQT09
Audiences: Everyone Is Invited
Contact: Miki Arlen
-
ECE-S Seminar - Dr Sabrina Neuman
Tue, Apr 11, 2023 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr Sabrina Neuman, Postdoctoral NSF Computing Innovation Fellow | Harvard University
Talk Title: Designing Computing Systems for Robotics and Physically Embodied Deployments
Abstract: Emerging applications that interact heavily with the physical world (e.g., robotics, medical devices, the internet of things, augmented and virtual reality, and machine learning on edge devices) present critical challenges for modern computer architecture, including hard real-time constraints, strict power budgets, diverse deployment scenarios, and a critical need for safety, security, and reliability. Hardware acceleration can provide high-performance and energy-efficient computation, but design requirements are shaped by the physical characteristics of the target electrical, biological, or mechanical deployment; external operating conditions; application performance demands; and the constraints of the size, weight, area, and power allocated to onboard computing-- leading to a combinatorial explosion of the computing system design space. To address this challenge, I identify common computational patterns shaped by the physical characteristics of the deployment scenario (e.g., geometric constraints, timescales, physics, biometrics), and distill this real-world information into systematic design flows that span the software-hardware system stack, from applications down to circuits. An example of this approach is robomorphic computing: a systematic design methodology that transforms robot morphology into customized accelerator hardware morphology by leveraging physical robot features such as limb topology and joint type to determine parallelism and matrix sparsity patterns in streamlined linear algebra functional units in the accelerator. Using robomorphic computing, we designed an accelerator for a critical bottleneck in robot motion planning and implemented the design on an FPGA for a manipulator arm, demonstrating significant speedups over state-of-the-art CPU and GPU solutions. Taking a broader view, in order to design generalized computing systems for robotics and other physically embodied applications, the traditional computing system stack must be expanded to enable co-design with physical real-world information, and new methodologies are needed to implement designs with minimal user intervention. In this talk, I will discuss my recent work in designing computing systems for robotics, and outline a future of systematic co-design of computing systems with the real world.
Biography: Sabrina M. Neuman is a postdoctoral NSF Computing Innovation Fellow at Harvard University. Her research interests are in computer architecture design informed by explicit application-level and domain-specific insights. She is particularly focused on robotics applications because of their heavy computational demands and potential to improve the well-being of individuals in society. She received her S.B., M.Eng., and Ph.D. from MIT. She is a 2021 EECS Rising Star, and her work on robotics acceleration has received Honorable Mention in IEEE Micro Top Picks 2022 and IEEE Micro Top Picks 2023.
Host: Dr Feifei Qian, feifeiqi@usc.edu | Dr Pierluigi Nuzzo, nuzzo@usc.edu
Webcast: https://usc.zoom.us/j/98275605184?pwd=NVBvL2hKdEZCRFRSTm1Hb1RWTSs2QT09More Information: ECE Seminar Announcement 04.11.2023 - Sabrina Neuman.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 132
WebCast Link: https://usc.zoom.us/j/98275605184?pwd=NVBvL2hKdEZCRFRSTm1Hb1RWTSs2QT09
Audiences: Everyone Is Invited
Contact: Miki Arlen
-
Semiconductors & Microelectronics Technology Seminar - Qiushi Guo, Thursday, April 13th at 11am in EEB 248
Thu, Apr 13, 2023 @ 11:00 AM - 12:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Qiushi Guo, CUNY Advanced Science Research Center (ASRC)
Talk Title: Lithium niobate integrated nonlinear photonics: new devices and systems on an old material
Series: Semiconductors & Microelectronics Technology
Abstract: Despite being an old material in optical and microwave technologies in its bulk form, thin-film lithium niobate (TFLN) has recently emerged as one of the most promising integrated photonic platforms owing to its strong electro-optic (EO) coefficient, quadratic optical nonlinearity, and broadband optical transparency ranging from 250 nm to 5 um. In this talk, I will first overview the basic optical properties of LN, and how LN nanophotonics can grant us new regimes of nonlinear photonics. Then I will present some of our recent experimental results on the realization and utilization of dispersion-engineered and quasi-phase-matched ultrafast photonic devices in both classical and quantum domains. I will discuss the realization of 100 dB/cm optical parametric amplification, 1.5-3 um widely tunable optical parametric oscillator (OPO), ultra-wide bandwidth quantum squeezing, femtosecond and femtojoule on chip all-optical switching, and the integrated mode-locked lasers based on TFLN with watt-level peak power.
Biography: Qiushi Guo is an assistant professor at the Advanced Science Research Center, City University of New York. Prior to joining the ASRC and the CUNY Graduate Center, Qiushi was a postdoctoral research associate at the California Institute of Technology. He received his Ph.D. in Electrical Engineering from Yale University in Dec. 2019, advised by Prof. Fengnian Xia. He received his M.S. degree in Electrical Engineering from the University of Pennsylvania in 2014, and his B.S. degree in Electrical Engineering from Xi'an Jiaotong University in 2012. Qiushi is the finalist of the 2022 Rising Star of Light, and the winner of the 2021 Henry Prentiss Becton Graduate Prize for his exceptional research achievements at Yale University. His research interests include integrated nonlinear and quantum photonics, mid-infrared photonics, and 2-D materials optoelectronics. He has published more than 40 peer-reviewed research papers in leading scientific journals with citations more than 300 times. He is serving on the editorial board of the journal Micromachines.
Host: J Yang, H Wang, C Zhou, S Cronin, W Wu
More Information: Qiushi Guo_2023-4-13.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski