Logo: University of Southern California

Events Calendar



Select a calendar:



Filter March Events by Event Type:



Events for March 02, 2022

  • ECE Seminar: Full Stack Deep Learning at the Edge

    Wed, Mar 02, 2022 @ 10:00 AM - 11:00 AM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars


    Speaker: Dr. Amir Gholami, Research Scientist, RiseLab and BAIR at UC Berkeley

    Talk Title: Full Stack Deep Learning at the Edge

    Abstract: An important next milestone in machine learning is to bring intelligence to the edge without relying on the computational power of the cloud. This could lead to more reliable, lower latency, and privacy preserving AI for a wide range of applications. However, state-of-the-art NN models require prohibitive amounts of compute, memory, and energy resources which is often not available at the edge. Addressing these challenges without compromising on accuracy, requires a multi-faceted approach, including hardware-aware model compression and accelerator co-design.

    In this talk, I will first discuss a novel hardware-aware method for neural network quantization and pruning that achieves optimal trade-off between accuracy, latency, and model size. In particular, I will discuss a new Hessian Aware Quantization (HAWQ) method that relies on second-order information to perform low precision quantization of the model with minimal generalization loss. I will present extensive testing of the method on different learning tasks including various models for image classification, object detection, natural language processing, and speech recognition showing that HAWQ exceeds previous baselines. I will then present a recent extension of this method which allows integer-only inference for the end-to-end computations, enabling efficient deployment on fixed-point hardware. Finally, I will discuss a full-stack hardware-aware neural network architecture and accelerator design, which enables adapting the model architecture and the accelerator parameters to achieve optimal performance.

    Related paper:
    ICML'21: HAWQ-V3: Dyadic Neural Network Quantization
    ICML'21: I-BERT: Integer-only BERT Quantization

    Biography: Amir Gholami is a research scientist in RiseLab and BAIR at UC Berkeley. He received his PhD from UT Austin, working on large scale 3D image segmentation, a research topic which received UT Austin's best doctoral dissertation award in 2018. He is a Melosh Medal finalist, the recipient of best student paper award in SC'17, Gold Medal in the ACM Student Research Competition, best student paper finalist in SC'14, as well as Amazon Machine Learning Research Award in 2020. He was also part of the Nvidia team that for the first time made low precision neural network training possible (FP16), enabling more than 10x increase in compute power through tensor cores. That technology has been widely adopted in GPUs today. Amir's current research focuses on efficient AI, AutoML, and scalable training of Neural Network models.


    Host: Host: Dr. Massoud Pedram, pedram@usc.edu

    Webcast: https://usc.zoom.us/j/95064180366?pwd=SVJ3VzZ3aGNRKzNLdmJQeGRhdzBUZz09

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248

    WebCast Link: https://usc.zoom.us/j/95064180366?pwd=SVJ3VzZ3aGNRKzNLdmJQeGRhdzBUZz09

    Audiences: Everyone Is Invited

    Contact: Mayumi Thrasher

    OutlookiCal
  • Center of Autonomy and AI, Center for Cyber-Physical Systems and the Internet of Things, and Ming Hsieh Institute Seminar Series

    Wed, Mar 02, 2022 @ 11:00 AM - 12:00 PM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars


    Speaker: Dimos V. Dimarogonas, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology

    Talk Title: Multi-robot Task Planning and Control Under Spatiotemporal Specifications

    Series: Center for Cyber-Physical Systems and Internet of Things

    Abstract: Multi-robot task planning and control under temporal logic specifications has been gaining increasing attention in recent years due to its applicability among others in autonomous systems, manufacturing systems, service robotics and intelligent transportation. Initial approaches considered qualitative logics, such as Linear Temporal Logic, whose automata representation facilitates the direct use of model checking tools for correct-by-design control synthesis. In many real world applications however, there is a need to quantify spatial and temporal constraints, e.g., in order to include deadlines and separation assurance bounds. This led to the use of quantitative logics, such as Metric Interval and Signal Temporal Logic, to impose such spatiotemporal constraints. However, the lack of automata representations for such specifications hinders the direct use of model checking tools. Motivated by this, the use of transient control methodologies that fulfil the aforementioned qualitative constraints becomes evident. In this talk, we review some of our recent results in applying transient control techniques, and in particular Model Predictive Control, Barrier Certificates based design and Prescribed Performance Control, to distributed multi-robot task planning under spatiotemporal specifications. The results are supported by relevant experimental validations.

    Biography: Dimos V. Dimarogonas received the Diploma in Electrical and Computer Engineering in 2001 and the Ph.D. in Mechanical Engineering in 2007, both from National Technical University of Athens (NTUA), Greece. Between 2007 and 2010, he held postdoctoral positions at the KTH Royal Institute of Technology, Dept of Automatic Control and MIT, Laboratory for Information and Decision Systems (LIDS). He is currently Professor at the Division of Decision and Control Systems, School of Electrical Engineering and Computer Science, at KTH. His current research interests include multi-agent systems, hybrid systems and control, robot navigation and manipulation, human-robot-interaction and networked control. He serves in the Editorial Board of Automatica and the IEEE Transactions on Control of Network Systems and is a Senior Member of IEEE. He is a recipient of the ERC Starting Grant in 2014, the ERC Consolidator Grant in 2019, and the Knut och Alice Wallenberg Academy Fellowship in 2015.

    Host: Pierluigi Nuzzo, nuzzo@usc.edu

    Webcast: https://usc.zoom.us/webinar/register/WN_zyIBh_1gQLmKpMJG0GyLxw

    Location: Online

    WebCast Link: https://usc.zoom.us/webinar/register/WN_zyIBh_1gQLmKpMJG0GyLxw

    Audiences: Everyone Is Invited

    Contact: Talyia White

    OutlookiCal
  • Evaluating & Negotiating Job Offers Workshop (HYBRID)

    Wed, Mar 02, 2022 @ 01:00 PM - 01:30 PM

    Viterbi School of Engineering Career Connections

    Workshops & Infosessions


    THIS EVENT WILL BE HOSTED HYBRID: IN-PERSON & ONLINE SIMULTANEOUSLY

    Consider best practices on evaluating and negotiating job or internship offers by attending this professional development Q&A moderated by Viterbi Career Connections staff or Viterbi employer partners.

    To access the ZOOM link and for more information on this workshop, log into Viterbi Career Gateway>> Events>>Workshops: https://shibboleth-viterbi-usc-csm.symplicity.com/sso/

    For more information about workshops, please visit viterbicareers.usc.edu/workshops.

    For In-Person: Attendance is limited to room capacity

    Location: Ronald Tutor Hall of Engineering (RTH) - 211

    Audiences: Everyone Is Invited

    Contact: RTH 218 Viterbi Career Connections

    OutlookiCal
  • AME Seminar

    Wed, Mar 02, 2022 @ 03:30 PM - 04:30 PM

    Aerospace and Mechanical Engineering

    Conferences, Lectures, & Seminars


    Speaker: Michael Burke, Columbia University

    Talk Title: Non-Equilibrium Behavior in Combustion, Planetary Atmospheres, and Compressible Flows

    Abstract: Chemically reacting flows are often interpreted and computed under the premise that all chemical species have a range of energies in their rotational and vibrational modes that are well described by the Boltzmann or thermal distribution at the local temperature. Of course, breakdown in this premise can occur naturally as a result of chemical reactions, light absorption, and/or shock waves. The manifestations of this breakdown on unimolecular reactions, where non-thermally distributed molecular ensembles dissociate, are well known to give rise to pressure-dependent reactions in combustion, photochemical reactions in the Earth atmosphere, and induction time lags in reactions following shock waves. By contrast, manifestations of non-equilibrium behavior on bimolecular reactions, where non-thermally distributed molecules react with other species, are generally less understood and historically less appreciated. Here, I describe three distinct tales of such non-equilibrium behavior across varied application domains. In particular, I present results from ab initio master equation calculations that shed light on previous hypotheses and experimental observations and reveal new processes involving non-equilibrium induced by chemistry in combustion, photons in the Earth atmosphere, and shock waves in compressible flows. Namely, the rovibrationally excited ephemeral complexes, formed from association of two molecules, with a third molecule give rise to a fourth, long-forgotten type of phenomenological reaction, involving three chemical reactants, that impacts macroscopic combustion behavior; the vibrationally excited complexes, formed upon photon absorption, collide with oxygen to produce radicals even for low photon energies in the Earth troposphere; and the rovibrationally cold molecular ensembles encountered following shock waves not only slow the reaction timescales but also change the main chemical pathways.

    Biography: Michael Burke is an Associate Professor of Mechanical Engineering at Columbia University, where he also holds affiliate appointments in Chemical Engineering and the Data Science Institute. Prior to joining Columbia in 2014, Burke earned his Ph.D. in Mechanical and Aerospace Engineering in 2011 at Princeton University, where he was a Wallace Memorial Honorific Fellow, and he worked as a Directors Postdoctoral Fellow in the Chemical Sciences and Engineering Division at Argonne National Laboratory. Burke is a recipient of the National Science Foundations CAREER award, the Combustion Institutes Research Excellence Award, the Combustion Institutes Hiroshi Tsuji Early Career Researcher Award, and the American Chemical Societys PRF Doctoral New Investigator Award. His publications have been featured in the News and Views section of Nature Chemistry, selected as the Feature Article in Combustion and Flame, and chosen for the Distinguished Paper Award at the 31st International Symposium on Combustion. His research combines physics and data across multiple scales to unravel and predict outcomes of complex reacting systems in varied application domains with major emphases on theoretical chemistry of nonequilibrium processes, multiscale datadriven modeling, and highthroughput experiments selected by optimal design.

    Host: AME Department

    More Info: https://usc.zoom.us/j/93987337017?pwd=MWd2dXBSL1FaR1RPaHNscjJ1NW80UT09

    Webcast: https://usc.zoom.us/j/93987337017?pwd=MWd2dXBSL1FaR1RPaHNscjJ1NW80UT09

    Location: James H. Zumberge Hall Of Science (ZHS) - 252

    WebCast Link: https://usc.zoom.us/j/93987337017?pwd=MWd2dXBSL1FaR1RPaHNscjJ1NW80UT09

    Audiences: Everyone Is Invited

    Contact: Tessa Yao

    OutlookiCal
  • A Study Break w/ Tesla: Weekly Series

    Wed, Mar 02, 2022 @ 06:00 PM - 06:45 PM

    Viterbi School of Engineering Career Connections

    Workshops & Infosessions


    A Study Break w/ Tesla is a series of professional workshops presented by the Hardware + Cell Engineering Internship Recruiting Team that will be offered on Wednesday evenings from February through April, 6:00 pm -6:45 pm.

    Each event will offer a 25-minute presentation on a specific topic, followed by a 20-minute opportunity for participants to ask questions and network with the Tesla team.

    Event: Personal Branding through LinkedIn and Handshake | March 2
    RSVP in Gateway

    This session will cover the importance of building strong candidate profiles on LinkedIn and Handshake, as well as strategies to maximize success and response rates on both career sites.

    External employer-hosted events and activities are not affiliated with the USC Career Center. They are posted on Viterbi Career Connections because they may be of interest to members of the Viterbi community. Inclusion of any activity does not indicate USC sponsorship or endorsement of that activity or event. It is the participant's responsibility to apply due diligence, exercise caution when participating, and report concerns to vcareers@usc.edu

    Location: Virtual

    Audiences: Everyone Is Invited

    Contact: RTH 218 Viterbi Career Connections

    OutlookiCal