Logo: University of Southern California

Events Calendar

Select a calendar:

Filter November Events by Event Type:

Events for November 14, 2017

  • PhD Defense- Dehua Cheng

    Tue, Nov 14, 2017 @ 10:00 AM - 12:00 PM

    Computer Science

    University Calendar

    Tuesday, November, 14th, 10 a.m. to 12 p.m., PHE 223

    Title: Improving machine learning algorithms with efficient data relevance discovery


    This is the era of big data, where both challenges and opportunities lie ahead for the machine learning research. The data are created nowadays at an unprecedented pace with an unignorable cost in collecting, storing, and computing with the current scale of data. As the computational power that we possess gradually plateaus, it is an ever-increasing challenge to fully utilize the wealth of big data, where better data reduction techniques and scalable algorithms are the keys to a solution. We observe that to answer a certain query, the data are not equally important. Based on the models and the query, we provide efficient access to the numerical scores of the data points that represent their relevance in the current task. It enables us to wisely devote the computation resources to the important data, which improves the scalability and the reliability. We present our work under three applications: 1) tensor CP decomposition, 2) random-walk matrix-polynomial sparsification, where we provide an efficient access to the statistical leverage score for a faster numerical routine; and 3) matrix completability analysis, where we analyze the underlying completability structure for a more reliable estimation.

    Location: Charles Lee Powell Hall (PHE) - 223

    Audiences: Everyone Is Invited

    Posted By: Lizsl De Leon

  • Enabling Effective Performance Optimization Techniques for Heterogeneous System

    Tue, Nov 14, 2017 @ 10:30 AM - 12:00 PM

    Ming Hsieh Department of Electrical Engineering

    Conferences, Lectures, & Seminars

    Speaker: Yun (Eric) Liang, Peking University, China

    Talk Title: Enabling Effective Performance Optimization Techniques for Heterogeneous System

    Abstract: Heterogeneous systems that couple CPUs with accelerators such as Graphics Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs) have become ubiquitous in the computing world due to their tremendous computing power. However, performance tuning for GPUs and FPGAs is not trivial. In this talk, I will first present the performance modeling and optimization for FPGAs. I will introduce an accurate performance model for OpenCL workloads on FPGAs and how we accelerate deep learning applications on FPGAs. For the second half of the talk, I will present on-chip storage and machine learning optimization techniques for GPUs. The proposed techniques leverage on compile-time and run-time techniques to improve the cache performance, register utilization, pipeline utilization and overall performance.

    Biography: Yun (Eric) Liang is an assistant professor in School of EECS, Peking University, China. His research focuses on energy-efficient heterogeneous computing, computer architecture, compilation techniques, electronic design automation and embedded system design. He has authored over 60 scientific publications in premier international journals and conferences in this domain. His research has been recognized by best paper award at FCCM 2011 and ICCAD 2017 and best paper nominations at DAC 2017, ASPDAC 2016, DAC 2012, FPT 2011, CODES+ISSS 2008. Prof Liang serves as Associate Editor for ACM Transactions in Embedded Computing Systems (TECS) and serves in the program committees in the premier conferences in the related domain including (HPCA, PACT, CGO, ICCAD, ICS, CC, DATE, CASES, ASPDAC, ICCD).

    Host: Xuehai Qian, x04459, xuehai.qian@usc.edu

    Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132

    Audiences: Everyone Is Invited

    Posted By: Gerrielyn Ramos

  • Academic Career Mentoring Panel Series

    Tue, Nov 14, 2017 @ 12:00 PM - 02:00 PM

    Viterbi School of Engineering Doctoral Programs

    Conferences, Lectures, & Seminars

    Speaker: Faculty Panel, Viterbi School of Engineering

    Talk Title: Academic and Industry Paths: How to be Ready and in Demand for Both

    Abstract: Engineering is the most employable career choice, both in industry and academia. This panel will discuss the similarities and differences between academic and industry careers, and how to prepare for your career choice.

    Please visit the website to register.

    Host: Viterbi School of Engineering

    More Info: https://viterbigrad.usc.edu/instructional-support/events-workshops/phd-academic-career-mentoring-panel-series/

    Location: Social Sciences Building (SOS) - B46

    Audiences: Ph.D. and Postdoctoral

    Posted By: Tracy Charles

  • Epstein Institute Seminar, ISE 651

    Tue, Nov 14, 2017 @ 03:30 PM - 04:50 PM

    Daniel J. Epstein Department of Industrial and Systems Engineering

    Conferences, Lectures, & Seminars

    Speaker: Dr. Zhaoran Wang, Assistant Professor, Northwestern University (starting 2018)

    Talk Title: Taming Nonconvexity with Data

    Host: Prof. Meisam Razaviyayn

    More Information: November 14 , 2017.pdf

    Location: Ethel Percy Andrus Gerontology Center (GER) - GER 206

    Audiences: Everyone Is Invited

    Posted By: Grace Owh

  • MASCLE Machine Learning Seminar: Robert Schapire (Microsoft Research NYC) - The Contextual Bandits Problem: Techniques for Learning to Make High-Reward Decisions

    Tue, Nov 14, 2017 @ 03:30 PM - 04:50 PM

    Computer Science

    Conferences, Lectures, & Seminars

    Speaker: Robert Schapire, Microsoft Research NYC

    Talk Title: The Contextual Bandits Problem: Techniques for Learning to Make High-Reward Decisions

    Series: NVIDIA Distinguished Lecture Series in Machine Learning

    Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.

    We consider how to learn through experience to make intelligent decisions. In the generic setting, called the contextual bandits problem, the learner must repeatedly decide which action to take in response to an observed context, and is then permitted to observe the received reward, but only for the chosen action. The goal is to learn to behave nearly as well as the best policy (or decision rule) in some possibly very large and rich space of candidate policies. This talk will describe progress on developing general methods for this problem and some of its variants.

    Biography: Robert Schapire is a Principal Researcher at Microsoft Research in New York City. He received his PhD from MIT in 1991. After a short post-doc at Harvard, he joined the technical staff at AT&T Labs (formerly AT&T Bell Laboratories) in 1991. In 2002, he became a Professor of Computer Science at Princeton University. He joined Microsoft Research in 2014. His awards include the 1991 ACM Doctoral Dissertation Award, the 2003 Gödel Prize, and the 2004 Kanelakkis Theory and Practice Award (both of the last two with Yoav Freund). He is a fellow of the AAAI, and a member of both the National Academy of Engineering and the National Academy of Sciences. His main research interest is in theoretical and applied machine learning, with particular focus on boosting, online learning, game theory, and maximum entropy.

    Host: Haipeng Luo

    Location: Henry Salvatori Computer Science Center (SAL) - 101

    Audiences: Everyone Is Invited

    Posted By: Computer Science Department

  • VIRTUAL Workshop: Find More Jobs & Internships: Viterbi Career Gateway

    Tue, Nov 14, 2017 @ 04:00 PM - 05:00 PM

    Viterbi School of Engineering Career Connections

    Workshops & Infosessions

    Take part in a live tutorial to help you navigate Viterbi Career Gateway, a powerful job & internship search tool available ONLY to Viterbi students.

    To access this VIRTUAL workshop, go to https://bluejeans.com/169541893 and log in with your netID and password.

    Location: ONLINE

    Audiences: Everyone Is Invited

    Posted By: RTH 218 Viterbi Career Connections

  • CS Colloquium: Dr. Brian Milch (Google) - Combining Probabilistic and Neural Approaches for Text Classification

    Tue, Nov 14, 2017 @ 05:00 PM - 06:20 PM

    Computer Science

    Conferences, Lectures, & Seminars

    Speaker: Dr. Brian Milch, Google

    Talk Title: Combining Probabilistic and Neural Approaches for Text Classification

    Series: CS Colloquium

    Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.

    In the Semantic Signals group at Google Los Angeles, we build classifiers that label text with hundreds of human-defined categories across dozens of languages. Labeled training data is sparse, so we've found it essential to incorporate unsupervised learning methods that take advantage of unlabeled text. One of our tools is a probabilistic topic model that learns discrete "clusters" to explain word co-occurrence patterns in a large corpus, and then identifies the clusters that best explain a new document. Another tool is a neural net that learns embeddings of individual words in a continuous space. I'll discuss how these approaches play complementary roles in our text classification pipeline.

    Biography: Brian Milch is a software engineer at Google's Los Angeles office. He received a B.S. in Symbolic Systems from Stanford University in 2000, and a Ph.D. in Computer Science from U.C. Berkeley in 2006. He then spent two years as a post-doctoral researcher at MIT before joining Google in 2008. He has contributed to Google production systems for spelling correction, transliteration, and semantic modeling of text.

    Host: Fei Sha

    Location: Seeley G. Mudd Building (SGM) - 124

    Audiences: Everyone Is Invited

    Posted By: Computer Science Department

  • INCOSE-LA Chapter Speaker Meeting

    Tue, Nov 14, 2017 @ 05:15 PM - 07:30 PM

    Systems Architecting and Engineering, USC Viterbi School of Engineering

    Conferences, Lectures, & Seminars

    Speaker: Ryan Noguchi , Director of the Space Architecture Department in the Systems Engineering Division at The Aerospace Corporation

    Talk Title: Best Practices and Lessons Learned from Model-Based System Engineering Pilot Programs

    Series: INCOSE-LA Speaker Series

    Abstract: Model Based Systems Engineering (MBSE) can offer significant benefits to organizations responsible for managing their increasingly complex enterprises. However, implementing MBSE is not a straightforward task, and there are many pitfalls along the way. An incremental approach built on solid system architecting principles, focusing on supporting major stakeholder decisions, and informed by best practices and lessons learned from previous efforts offers the best chances of success. Five years of experience in working MBSE efforts at multiple levels have produced many lessons learned and recommended best practices. This report authored by Ryan Noguchi will be briefly summarized in his presentation.

    Cost: INCOSE Members: FREE. Non-members: $10 (refreshments provided). See the registration link below.

    Biography: Ryan Noguchi is the Director of the Space Architecture Department in the Systems Engineering Division at The Aerospace Corporation. Ryan received a B.S. in Mechanical and Aerospace Engineering from Princeton University and an M.S. in Mechanical Engineering from the University of California, Berkeley. He has been with The Aerospace Corporation for 20 years, and led numerous system acquisition, development, integration, and mission assurance efforts. His current responsibilities focus on the refinement and application of methodologies for model-based systems engineering, and system-of-systems engineering.

    From the 105 Freeway traveling WEST:
    1. Take the exit towards 405 South
    2. Before getting onto the 405 Freeway, take the El Segundo Blvd exit
    3. At the bottom of the ramp, turn left (west)
    4. Turn right on Aviation Blvd.
    5. Bldg. D8 will be on the third building on the Right, just past the discount bakery.
    The facility is the third building from the corner of Aviation and El Segundo, just north of the discount bakery outlet. The facility has 4 gates, but only the southern-most gate is open. Identify yourself to the security guard as attending the INCOSE meeting. You can park where Security directs and enter through the lobby at the center of the building where the flag poles are. Knock on the first of the double doors, and someone will open the door for you. The handicap ramp is on the north side and can be reached by driving all the way around the back of the building. Inform the security guard if you plan to use that ramp.

    Host: The Aerospace Corporation (Venue); INCOSE-Los Angeles (Event)

    More Info: http://events.constantcontact.com/register/event?llr=l4ihvgeab&oeidk=a07ee9oa8ta76968e83

    Location: The Aerospace Corporation, Building D8/1010, 200 N. Aviation, El Segundo, CA

    Audiences: Everyone Is Invited

    Posted By: James Moore II