Logo: University of Southern California

Events Calendar



Select a calendar:



Filter May Events by Event Type:



University Calendar
Events for May

  • WEBINAR SERIES: Digital Technologies for COVID-19

    Fri, May 01, 2020 @ 11:00 AM - 12:00 PM

    Information Sciences Institute, USC Viterbi School of Engineering

    University Calendar


    Our third webinar will feature a double-header of talks by researchers from USC Viterbi's Information Sciences Institute. The first talk will cover work by Pedro Szekely on a knowledge graph for COVID-19 papers, and the second talk will cover work by Jay Pujara on rapidly responding to COVID-19 using knowledge graphs.

    Please find abstracts for these talks as well as the speaker bios below:


    Talk 1: A Knowledge Graph Integrating Annotations On 44,000 COVID-19 Scientific Articles


    Pedro Szekely

    Abstract: The COVID-19 Open Research Dataset (CORD-19), compiled by the Allen Institute for AI is a free resource of over 44,000 scholarly articles, including over 29,000 with full text, about COVID-19 and the coronavirus family of viruses. At the ISI Center On Knowledge Graphs we are working to enrich this corpus with annotations obtained using multiple state of the art information extraction tools, bioinformatics databases, and multiple graph and network analytics. These tools are difficult to run and produce outputs in different formats, making it difficult for COVID-19 researchers to use them. We are building a knowledge graph that integrates the outputs of these tools and databases in a simple data model that we provide in multiple formats (TAB-separated, RDF/SPARQL and Neo4J) to facilitate use of the corpus annotations. Our current release enriches the CORD-19 corpus with gene, chemical, disease and taxonomic information from Wikidata and CTD databases, as well as entity extractions from Professor's Heng Ji BLENDER lab at UIUC. In the next releases we will also integrate extractions from the Reach project at University of Arizona and others.


    Bio: Dr. Pedro Szekely (Ph.D. Carnegie Mellon 1987) is a Principal Scientist and Research Director of the Center on Knowledge Graphs at the USC Information Sciences Institute (ISI), and a Research Associate Professor at the USC Computer Science Department. Dr. Szekely's research focuses on algorithms and tools for rapid construction of domain-specific knowledge graphs. The tools developed in his group have been used in several DARPA and IARPA projects to construct knowledge graphs in cyber security, causal exploration, hypothesis generation and forecasting of geo-political events, and has been used by law enforcement agencies to identify victims of human trafficking and to build legal cases against the traffickers. Dr. Szekely teaches a graduate course at USC on Building Knowledge Graphs, and has given tutorials on knowledge graph construction at KDD, ISWC, AAAI and WWW.


    Talk 2: Rapidly Responding to COVID-19 Using Knowledge Graphs

    Jay Pujara

    Abstract: Responding to the COVID-19 pandemic has created a need to navigate vast amounts of information and quickly make decisions. I will describe how knowledge graphs, structured repositories capturing interconnected information, can help quickly adapt to new circumstances. To illustrate the value of these techniques, I will describe two active projects in our research group. The first allows experts to sift through thousands of research papers and identify scientific results that are likely to be reproducible. The second helps manufacturers adapt their supply chains to develop health and safety projects. Both projects are the result of analyzing terabytes of data and developing a succinct representation that can help answer questions with rich information.

    Bio: Jay Pujara is a research assistant professor of Computer Science at the University of Southern California and a research lead at the Information Sciences Institute whose principal areas of research are machine learning, artificial intelligence, and data science. He completed a postdoc at UC Santa Cruz, earned his PhD at the University of Maryland, College Park and received his MS and BS at Carnegie Mellon University. Prior to his PhD, Jay spent six years at Yahoo! working on mail spam detection and user trust, and he has also worked at Google, LinkedIn and Oracle. Jay is the author of over thirty peer-reviewed publications and has received four best paper awards for his work. He is a recognized authority on knowledge graphs, and has organized the Automatic Knowledge Base Construction (AKBC) and Statistical Relational AI (StaRAI) workshops, presented tutorials on knowledge graph construction at AAAI and WSDM, and had his work featured in AI Magazine. For more information, visit https://www.jaypujara.org

    Series co-hosted by:
    Craig Knoblock, Executive Director, USC Information Sciences Institute
    Bhaskar Krishnamachari, Director, USC Viterbi Center for CPS and IoT

    WebCast Link: https://usc.zoom.us/webinar/register/WN_SnVYd9ONQgyYeLWiI8qtMA

    Audiences: Everyone Is Invited

    Contact: Bhaskar Krishnamachari

    OutlookiCal
  • Machine Learning to Track Epidemic Spread Featuring Viktor Prasanna

    Tue, May 05, 2020 @ 11:00 AM - 12:00 PM

    Viterbi School of Engineering Alumni

    University Calendar


    What technologies have evolved from a machine learning context that will help us in this unprecedented time? Join us for a live 60-minute webinar as Dr. Viktor Prasanna guides us through his development for a tool that will predict the global spread of the COVID-19 epidemic. He will share, for the first time, results from ReCOVER, his latest data model for accurate predictions and resource allocation for COVID-19 and other epidemics response. This webinar will feature a live Q&A session.

    Dr. Prasanna holds the Charles Lee Powell Chair in Engineering and is a professor of electrical engineering and a professor of computer science. His research interests include high performance computing, parallel and distributed systems, reconfigurable computing, cloud computing and smart energy systems. He received his bachelor's degree in electronics engineering from the Bangalore University, master's degree from the School of Automation, Indian Institute of Science and Ph.D. in computer science from the Pennsylvania State University. Prasanna received the W. Wallace McDowell Award from the IEEE Computer Society in 2015 for his contributions to reconfigurable computing. He received an Outstanding Engineering Alumnus Award from the Pennsylvania State University in 2009. He received a 2019 Distinguished Alumnus Award from the Indian Institute of Science (IISc). He is a Fellow of the IEEE, the Association for Computing Machinery (ACM) and the American Association for Advancement of Science (AAAS).

    Please use this link to sign up: https://viterbi-live-prasanna.eventbrite.com

    This session will be hosted on Zoom. Links and passwords will be sent to all registered participants the morning of May 5th.

    For any questions, please email us at engalums@usc.edu.

    Audiences: Everyone Is Invited

    Contact: Kristy Ly

    OutlookiCal
  • Prospective Students: Chat with a USC Rep

    Thu, May 07, 2020 @ 12:00 PM - 01:00 PM

    Viterbi School of Engineering Graduate Admission

    University Calendar


    Attendee Webex registration link:
    https://uscviterbi.webex.com/uscviterbi/onstage/g.php?MTID=e668d14a184ebcfda37c850b83222237e

    Interested in Master's or PhD programs in engineering or computer science?

    Meet representatives from the Viterbi School of Engineering on an online webinar!

    Students who have earned or are in the process of earning a Bachelor's degree in engineering, computer science, mathematics, or a hard science (such as physics, biology, or chemistry) are welcome to attend to learn more about applying to our graduate programs.

    The session will include information on the following topics:

    - Master's & PhD programs in engineering and computer science
    - How to Apply
    - Scholarships and funding
    - Student life at USC and in Los Angeles

    There will also be sufficient time for questions.

    We look forward to seeing you there.

    Location: Webex

    WebCast Link: https://uscviterbi.webex.com/uscviterbi/onstage/g.php?MTID=e668d14a184ebcfda37c850b83222237e

    Audiences: Prospective Graduate Students

    Contact: camila tabar

    OutlookiCal
  • AI for COVID-19 in LA (Virtual Symposium)

    Fri, May 08, 2020 @ 10:00 AM - 04:00 PM

    Information Sciences Institute, USC Viterbi School of Engineering

    University Calendar


    Machine Learning Center (MaSCle) and Center for Artificial Intelligence in Society (CAIS) proudly present: AI for COVID-19 in LA, a virtual symposium highlighting the role of data science and artificial intelligence in the evolving pandemic.

    COVID-19 is fundamentally changing societies, businesses, and governments around the world. With lock downs and other restrictions in place, and daily lives becoming virtual, the evolving situation has underscored the role of data science to analyze and develop insights into how resources and information are shaping our well-being.

    Join us as we bring together experts and leaders from the field of data science and artificial intelligence to seed research directions, reveal insights, and help communities across the world.

    This is a free virtual event, but registration is required.
    For further inquiries contact us at AI4COVID@gmail.com

    https://www.eventbrite.com/e/ai-for-covid-19-in-la-virtual-symposium-tickets-103861213686

    WebCast Link: https://www.eventbrite.com/e/ai-for-covid-19-in-la-virtual-symposium-tickets-103861213686

    Audiences: Everyone Is Invited

    Contact: Christina Loredo

    OutlookiCal
  • PhD Defense - Artem Molchanov

    Mon, May 11, 2020 @ 01:30 PM - 03:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Ph.D. Defense - Artem Molchanov 5/11 1:30 pm "Data Scarcity in Robotics: Leveraging Structural Priors and Representation Learning"

    Ph.D. Candidate: Artem Molchanov
    Date: Monday, May 11, 2020
    Time: 1:30 PM - 3:00 PM
    Committee: Gaurav S. Sukhatme (Chair), Nora Ayanian, Heather Culbertson, Satyandra K. Gupta
    Title: Data Scarcity in Robotics: Leveraging Structural Priors and Representation Learning

    Abstract:
    Recent advances in Artificial Intelligence have benefited significantly from access to large pools of data accompanied in many cases by labels, ground truth values, or perfect demonstrations. In robotics, however, such data are scarce or absent completely. Overcoming this issue is a major barrier to move robots from structured laboratory settings to the unstructured real world. In this thesis, by leveraging structural priors and representation learning, we provide several solutions when data required to operate robotics systems is scarce or absent.

    In the first part of this thesis we study sensory feedback scarcity. We show how to use high-dimensional alternative sensory modalities to extract data when primary sensory sources are absent. In a robot grasping setting, we address the problem of contact localization and solve it using multi-modal tactile feedback as the alternative source of information. We leverage multiple tactile modalities provided by piezoresistive and capacitive sensor arrays to structure the problem as spatio-temporal inference. We employ the representational power of neural networks to acquire the complex mapping between tactile sensors and the contact locations. We investigate scarce feedback due to the high cost of measurements. We study this problem in a challenging field robotics setting where multiple severely underactuated aquatic vehicles need to be coordinated. We show how to leverage collaboration among the vehicles and the spatio-temporal smoothness of the ocean currents as a prior to densify feedback about ocean currents to acquire better controllability.

    In the second part of this thesis, we investigate scarcity of the data related to the desired task. We develop a method to efficiently leverage simulated dynamics priors to perform sim-to-real transfer of a control policy when no data about the target system is available. We investigate this problem in the scenario of sim-to-real transfer of low-level stabilizing quadrotor control policies. We demonstrate that we can learn robust policies in simulation and transfer them to the real system while acquiring no samples from the real quadrotor. We consider the general problem of learning a model with a very limited number of samples using meta-learned losses. We show how such losses can encode a prior structure about families of tasks to create well-behaved loss landscapes for efficient model optimization. We demonstrate the efficiency of our approach for learning policies and dynamics models in multiple robotics settings.


    Meeting Links:
    Zoom Meeting:
    https://usc.zoom.us/j/98384775690
    Meeting ID: 983 8477 5690


    Google Meet (ONLY A BACKUP - IF WE EXPERIENCE PROBLEMS WITH ZOOM):
    Meeting ID:
    meet.google.com/unz-zwzs-nxj
    Phone Numbers:
    +1 470-735-5928
    PIN: 476 191 520#

    WebCast Link: https://usc.zoom.us/j/98384775690

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    OutlookiCal
  • PhD Defense - Zhiyun Lu

    Wed, May 20, 2020 @ 12:00 PM - 02:00 PM

    Thomas Lord Department of Computer Science

    University Calendar


    Ph.D. Candidate: Zhiyun Lu
    Date: Wednesday, May 20, 2020
    Time: 12:00 PM - 2:00 PM
    Committee: Fei Sha (Chair), Haipeng Luo, C.-C. Jay Kuo

    Title: Leveraging Training Information for Efficient and Robust Deep Learning

    Abstract: Deep neural nets have exhibited great success on a wide range of machine learning problems across various domains, such as speech, image, and text. Despite decent prediction performances, there are rising concerns for the `in-the-lab' machine learning models to be vastly deployed in the wild. In this thesis, we study two of the main challenges in deep learning: efficiency, computational as well as statistical, and robustness. We describe a set of techniques to solve the challenges by utilizing information from the training process intelligently. The solutions go beyond the common recipe of a single point estimate of the optimal model.

    The first part of the thesis studies the efficiency challenge. We propose a budgeted hyper-parameter tuning algorithm to improve the computation efficiency of hyper-parameter tuning in deep learning. It can estimate and utilize the trend of training curves to adaptively allocate resources for tuning, which demonstrates improved efficiency over state-of-the-art tuning algorithms. Then we study the statistical efficiency on tasks with limited labeled data. Specifically we focus on the task of speech sentiment analysis. We apply pre-training using automatic speech recognition data, and solve sentiment analysis as a downstream task, which greatly improves the data efficiency of sentiment labels.



    The second part of the thesis studies the robustness challenge. Motivated by the resampling method in statistics, we study the uncertainty estimate of neural networks by local perturbative approximations. We propose to sample replicas of the model parameters from a Gaussian distribution to form a pseudo-ensemble. The ensemble predictions are used to estimate the uncertainty of the original model, which improves its robustness against invalid inputs.


    Meeting links:


    Zoom: https://usc.zoom.us/j/96089712182 (Meeting ID: 960 8971 2182)


    Google Meet (backup): meet.google.com/nxz-eybf-urw

    WebCast Link: https://usc.zoom.us/j/96089712182

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    OutlookiCal
  • WEBINAR SERIES: Digital Technologies for COVID-19

    Fri, May 29, 2020 @ 11:00 AM - 12:00 PM

    Information Sciences Institute, USC Viterbi School of Engineering

    University Calendar


    Our next webinar in the continuing series will feature a double-header of talks as well. First, Prof. John Heidemann from USC Viterbi's Information Sciences Institute will present his work analyzing Internet traffic during the COVID-19 outbreak. Then, Dr. Animesh Pathak, a Viterbi industry alum who heads R&D and Engineering at myKaarma, will discuss the experiences of an automobile business software company in addressing unique challenges posed by COVID-19.


    Talk 1: A First Look at Measuring the Internet during Novel Coronavirus to Evaluate Quarantine (MINCEQ) -- by John Heidemann

    Abstract: Measuring the Internet during Novel Coronavirus to Evaluate Quarantine (RAPID-MINCEQ) is a project to measure changes in Internet use during the COVID-19 outbreak of 2020.

    Today social distancing and work-from-home/study-from-home are the best tools we have to limit COVID's spread. But implementation of these policies varies in the US and around the global, and we would like to evaluate participation in these policies.

    This project plans to develop two complementary methods of assessing Internet use by measuring address activity and how it changes relative to historical trends. Changes in the Internet can reflect work-from-home behavior. Although we cannot see all IP addresses (many are hidden behind firewalls or home routers), early work shows changes at USC and ISI.

    This project is support by an NSF RAPID grant for COVID-19 and just began in May 2020, so this talk will discuss directions we plan to explore.

    Bio: John Heidemann is a principal scientist at the University of Southern California/Information Sciences Institute (USC/ISI) and a research professor at USC in Computer Science. At ISI he leads the ANT (Analysis of Network Traffic) Lab, studying how to observe and analyze Internet topology and traffic to improve network reliability, security, protocols, and critical services. He is a senior member of ACM and fellow of IEEE.


    Talk 2: Tales from the field: addressing COVID-19 challenges from the perspective of automotive business software -- by Animesh Pathak

    Abstract: COVID-19 caught everyone by surprise, including businesses that have traditionally relied on in-person contact to serve their customers. In the view of changing social norms and new social distancing safety guidelines, many businesses have had to quickly pivot or risk closing down.

    In this talk, I will share observations from the US and Canadian automotive dealership industry's efforts to overcome these new challenges, and the resulting process and software changes that had to be made to enable their vision, including the recent "Mobile Service" initiative by a major luxury automotive brand. I will share a glimpse of the various interesting system-building and computer science problems arising from the new reality that is here to stay, and the resulting opportunities for real-world impact to livelihoods of workers.

    Bio: Dr. Animesh Pathak is the Head of R&D and Head of Engineering at myKaarma, where he is responsible for the overall reliability, scalability, and security of myKaarma products in the areas of unified communication, payments, video inspections, scheduling, and logistics for Automotive OEMs and Dealerships in the US and Canada. myKaarma is headquartered in Long Beach, California, with offices in Canada and India.

    Previously, Dr. Pathak was a Research Scientist at Inria in Paris. He received his Ph.D in Computer Engineering from the Viterbi School of Engineering at USC, and the B.Tech. degree in Computer Science and Engineering from the Indian Institute of Technology, Banaras Hindu University (IIT BHU), where he was awarded the Institute Gold Medal.

    WebCast Link: https://usc.zoom.us/webinar/register/WN_bS2IGZDMTw2aymiLaBAzIw

    Audiences: Everyone Is Invited

    Contact: Bhaskar Krishnamachari

    OutlookiCal