Logo: University of Southern California

Events Calendar



Select a calendar:



Filter May Events by Event Type:



Events for the 1st week of May

  • Study Day

    Sun, Apr 29, 2018

    Viterbi School of Engineering Student Affairs

    University Calendar


    Audiences: Everyone Is Invited

    Contact: Sheryl Koutsis

    OutlookiCal
  • Study Day

    Mon, Apr 30, 2018

    Viterbi School of Engineering Student Affairs

    University Calendar


    Audiences: Everyone Is Invited

    Contact: Sheryl Koutsis

    OutlookiCal
  • Rapid, Efficient, and Robust Neuroimage Analysis with Deep Neural Networks

    Mon, Apr 30, 2018 @ 11:30 AM - 12:30 PM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars


    Speaker: Mert R. Sabuncu, Electrical and Computer Engineering, Cornell University

    Talk Title: Rapid, Efficient, and Robust Neuroimage Analysis with Deep Neural Networks

    Series: Medical Imaging Seminar Series

    Abstract: Abstract: Neuroimaging is entering a new era of unprecedented scale and complexity. Soon, we will have datasets including brain images from more than 100,000 individuals. The fundamental challenges in analyzing and exploiting these data are going to be computational. Today, widely-used traditional neuroimage analysis tools, such as FreeSurfer or FSL, are computationally demanding and offer limited flexibility, while cutting-edge tools based on modern machine learning techniques require large amounts of annotated training data, and/or are untested at scale. In this talk, I will present our recent work on two fundamental image analysis problems: registration and segmentation. In image registration, I will introduce a novel framework that allows us to train a neural network that rapidly computes a smooth and invertible nonlinear (diffeomorphic) deformation that aligns two input images, in an unsupervised fashion (i.e. without using ground-truth registrations). I will show experiments on 7000+ brain MRI scans with state-of-the-art results. In the second part, I will present a new segmentation framework that flexibly handles multiple labeling protocols, and generalizes well to new datasets and new segmentation labels, with little additional training.

    Biography: Mert R. Sabuncu is a faculty member of Cornel's School of Electrical Engineering and Computer Engineering.At Cornell, Mert directs a lab that focuses on biomedical image analysis for scientific (e.g. brain mapping) and clinical (e.g., computer-aided diagnosis) applications.Mert's research employs and contributes to the toolkits of machine learning, image processing, computer vision, and other modern computational methods.Mert has a Ph.D. from Princeton Electrical Engineering and was post-doc at MIT, where he worked with Polina Golland. Before joining Cornell, he was a faculty member at the A.A. Martinos Center for Biomedical Imaging (Harvard Medical School and Massachusetts General Hospital).

    Host: Professor Richard Leahy

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

    Audiences: Everyone Is Invited

    Contact: Talyia White

    OutlookiCal
  • PhD Defense - Stephanie Kemna

    Mon, Apr 30, 2018 @ 02:00 PM - 04:00 PM

    Computer Science

    University Calendar


    PhD Candidate: Stephanie Kemna

    Committee: Gaurav Sukhatme (chair), Nora Ayanian, David Caron

    Title: Multi-Robot Strategies for Adaptive Sampling with Autonomous Underwater Vehicles
    Time & place: Monday April 30th, 2pm, RTH406
    Abstract:
    Biologists and oceanographers are sampling lakes and oceans worldwide, to obtain data on the natural phenomena they are interested in. For example, measuring algae abundance to understand and explain potentially harmful algal blooms. Typical methods of sampling are (a) taking physical water samples and sensor measurements from boats, (b) deploying sensor packages off of buoys, docks or other static man-made structures, and more recently (c) running pre-programmed missions with aquatic robots. The use of robot teams could significantly improve cost- and time-efficiency of lake and ocean sampling, allowing persistent and efficient mapping of the water column in finer resolution. Additionally, these systems may be able to intelligently gather data without needing a lot of prior information. We envision a scenario where one or two groups of biologists or oceanographers come together for monitoring a lake, bringing their autonomous vehicles with biological sensors.
    Our focus is on improving sampling efficiency, and environmental modeling performance, through the addition of (decentralized) coordination approaches for multi-robot sampling systems. In this presentation, I will discuss adaptive informative sampling techniques for single- and multi-robot deployments. Adaptive informative sampling means that the robots adapt their trajectory online, based on sampled data, while incorporating information-theoretic metrics to seek out the most informative sampling locations. Through simulation studies we have shown the benefits that can be obtained from employing adaptive informative sampling approaches. We include field results to show the feasibility of running adaptive informative sampling on board an autonomous underwater vehicle (AUV).
    For the multi-robot case, we show the benefits that can be obtained from adding data sharing between vehicles, and we explore the trade-off of surface based (Wi-Fi) communications versus underwater (acoustic) communications. In terms of coordinating multiple vehicles, I will first discuss an explicit coordination approach, based on dynamic estimation of Voronoi partitions, which shows potential for improving modeling performance in the early stages of model creation. I then discuss a method we developed for how to best start adaptive sampling runs when no prior data is available. Finally, I will discuss the use of implicit coordination through asynchronous surfacing with a surface-based data hub. We showed that performance across surfacing strategies was similar, though some turned out to be less consistent in performance, and some methods showed potential for greatly reducing the number of surfacing events needed.
    Overall, I have developed several methods for adaptive informative sampling with AUVs, focusing on multi-robot coordination and field constraints. The results of my studies show the benefits and potential of incorporating data sharing and coordination strategies into adaptive sampling routines for multi-robot systems.



    Location: Ronald Tutor Hall of Engineering (RTH) - 406

    Audiences: Everyone Is Invited

    Contact: Lizsl De Leon

    OutlookiCal
  • Tumo Workshops Information Session

    Mon, Apr 30, 2018 @ 05:00 PM - 07:00 PM

    Information Technology Program (ITP)

    Workshops & Infosessions


    How does the opportunity to share the skills you've learned at the Information Technology Program sound? Now's your chance to design and propose a workshop of your choice to teach students this summer at the Tumo Center for Creative Technologies in Armenia; expenses, including airfare and accommodation, are covered by Tumo.

    Tumo is an innovative digital media studio where students are guided by skilled educators and media professionals in animation, digital media, video game design, and web development. Workshops are hands-on and result in a group or individual project that students can exhibit in a final presentation. Each workshop is taught in the afternoon and can include one or several groups of around 20 teens. Workshop leaders usually visit for a minimum of two weeks, depending on the workshop's topic.

    Ready to learn more? ITP will be hosting a representative from Tumo to discuss this summer opportunity on Monday, April 30 at 5p.m. in KAP 160. We hope you can join us to learn more about this opportunity.

    Location: Kaprielian Hall (KAP) - 160

    Audiences: Undergrad

    Contact: Tim Gotimer

    OutlookiCal
  • Study Day

    Tue, May 01, 2018

    Viterbi School of Engineering Student Affairs

    University Calendar


    Audiences: Everyone Is Invited

    Contact: Sheryl Koutsis

    OutlookiCal
  • Epstein Institute Seminar, ISE 651

    Tue, May 01, 2018 @ 03:30 PM - 04:50 PM

    Daniel J. Epstein Department of Industrial and Systems Engineering

    Conferences, Lectures, & Seminars


    Speaker: Dr. Brian Denton, Professor, University of Michigan, Ann Arbor

    Talk Title: Optimization of Biomarker-Based Screening Strategies for Early Detection of Prostate Cancer

    Host: Dr. Sze-chuan Suen

    More Information: May 1, 2018.pdf

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

    Audiences: Everyone Is Invited

    Contact: Grace Owh

    OutlookiCal
  • 2018 Game Industry Careers Night

    Tue, May 01, 2018 @ 07:00 PM - 09:00 PM

    Information Technology Program (ITP)

    Workshops & Infosessions


    As you prepare to graduate and start the next level as a working professional in the video game industry, join the Information Technology Program for an exciting night of discussion with game programmers, level designers, producers, and consultants.

    Students in Video Game Design and Management, Video Game Programming, Computer Science (Games), and Interactive Media and Games are all welcome to attend, as are any students who are interested in learning about the transforming video game industry. Refreshments will be provided.

    This is event is organized and moderated by Professor Tom Sloper, who brings his experience at Activision, Sega, Atari, and Yahoo to develop and teach courses in video game design, production, and management at the USC Viterbi School of Engineering.

    Location: Kaprielian Hall (KAP) - 160

    Audiences: Undergrad

    Contact: Tim Gotimer

    OutlookiCal
  • A Surge-type Pricing in Ridesharing Systems is Stability Optimal

    Thu, May 03, 2018 @ 10:00 AM - 11:00 AM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars


    Speaker: Costas Courcoubetis, Singapore University of Technology and Design (SUTD)

    Talk Title: A Surge-type Pricing in Ridesharing Systems is Stability Optimal

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

    Abstract: The availability of drivers at a certain location affects the waiting time of passengers that arrive to be served by the platform.We introduce a queueing model for this waiting time and consider the effect on stability of available drivers' mobility pattern, their willingness to accept rides in a given location, and the incentives offered by the platform. For any fixed number of drivers, we characterize the largest set of passenger arrival rates which can result to stable queues under some policy dictating the movement of available drivers and their acceptance of rides. It turns out that any such policy can be enforced by offering appropriate region-dependent rewards to drivers for passenger pick up. Next, we show that dynamic rewards which are proportional to the passenger queue lengths, have the property of stabilizing queues for any arrival rates within the stability region. Seen from the perspective of drivers, such rewards which resemble surge pricing maximize their utilization.

    Biography: Prof. Costas A Courcoubetis was born in Athens, Greece and received his Diploma (1977) from the National Technical University of Athens, Greece, in Electrical and Mechanical Engineering, his MS (1980) and PhD (1982) from the University of California, Berkeley, in Electrical Engineering and Computer Science. He was MTS at the Mathematics Research Center, Bell Laboratories, Professor in the Computer Science Department at the University of Crete, Professor in the Department of Informatics at the Athens University of Economics and Business, and Professor in the ESD Pillar, Singapore University of Technology and Design where he heads the Initiative for the Sharing Economy and co-directs the new ST-SUTD Center for Smart Systems. His current research interests are economics and performance analysis of networks and internet technologies, sharing economy, regulation policy, smart grids and energy systems, resource sharing and auctions. Besides leading in the past a large number of research projects in these areas he has also published over 100 papers in scientific journals such as Operations Research, Mathematics of Operations Research, Journal on Applied Probability, ToN, IEEE Transactions in Communications, IEEE JSAC, SIAM Journal on Computing, etc. and in conferences such as FOCS, STOC, LICS, INFOCOM. GLOBCOM, ITC, ACM SIGMETRICS. His work has over 13,000 citations according to the Google Scholar. He is co-author with Richard Weber of "Pricing Communication Networks: Economics, Technology and Modeling" (Wiley, 2003).


    Host: Professor Bhaskar Krishnamachari

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

    Audiences: Everyone Is Invited

    Contact: Talyia White

    OutlookiCal
  • : Building Safe and Secure Cyber-Physical Systems Against All Odds

    Fri, May 04, 2018 @ 02:00 PM - 03:00 PM

    Ming Hsieh Department of Electrical and Computer Engineering

    Conferences, Lectures, & Seminars


    Speaker: Radoslav Ivanov, University of Pennsylvania

    Talk Title: Building Safe and Secure Cyber-Physical Systems Against All Odds

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

    Abstract: The increased autonomy of modern Cyber-Physical Systems (CPS) has exposed our limited understanding of systems of such complexity. Multiple deadly accidents in different domains (e.g., automotive, medical, aircraft) have occurred in the last several years, some due to partially known and changing (physiological) models and some due to malicious attacks that disrupt the system operation. In this talk, I will discuss my work on ensuring the safety and security of modern CPS; in particular, my focus is on providing accurate information with guarantees as a necessary condition to closing the loop. In the Medical CPS domain, I have developed parameter-invariant and context-aware detection and estimation approaches with guaranteed performance regardless of the values of unknown patient-specific physiological parameters (e.g., metabolic rate). We have successfully applied these approaches on real-patient data from the Children's Hospital of Philadelphia for the purpose of monitoring the patient's oxygen content during surgery.

    In the CPS security domain, my work makes use of the inherent sensor redundancy available in modern CPS in order to argue about the system safety and security even when some components might be under attack. In particular, I have proposed attack-resilient sensor fusion techniques that do not require any assumptions about which particular sensors fail or are under attack in order to detect safety-critical states. We have evaluated the benefit of sensor fusion in a number of automotive CPS applications where the system has access to multiple sensors that can be used to estimate the same state (e.g., velocity can be estimated using encoders, cameras, GPS, etc.).

    Biography: Radoslav Ivanov received the B.A. degree in computer science and economics from Colgate University, NY, and the Ph.D. degree in computer and information science from the University of Pennsylvania. He is currently a postdoctoral researcher at the University of Pennsylvania, working with Insup Lee and James Weimer. Radoslav's research interests include the design and control of safe and secure cyber-physical systems, in particular, automotive and medical CPS, and predictive and retrospective analysis of medical patient data.

    Host: Professor Paul Bogdan

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

    Audiences: Everyone Is Invited

    Contact: Talyia White

    OutlookiCal
  • NL Seminar-Neural Creative Language Generation PhD Defense Practice Talk

    Fri, May 04, 2018 @ 03:00 PM - 04:00 PM

    Information Sciences Institute

    Conferences, Lectures, & Seminars


    Speaker: Marjan Ghazvininejad , USC/ISI

    Talk Title: Neural Creative Language Generation PhD Defense Practice Talk

    Series: Natural Language Seminar

    Abstract: Natural language generation is a well studied and still very challenging field in natural language processing. One of the less studied NLG tasks is the generation of creative texts such as jokes, puns, or poems. Multiple reasons contribute to the difficulty of research in this area. First, no immediate application exists for creative language generation. This has made the research on creative NLG extremely diverse, having different goals, assumptions, and constraints. Second, no quantitative measure exists for creative NLG tasks. Consequently, it is often difficult to tune the parameters of creative generation models and drive improvements to these systems. Lack of a quantitative metric and the absence of a well-defined immediate application makes comparing different methods and finding the state of the art an almost impossible task in this area. Finally, rule-based systems for creative language generation are not yet combined with deep learning methods. Rule based systems are powerful in capturing human knowledge, but it is often too time-consuming to present all the required knowledge in rules. On the other hand, deep learning models can automatically extract knowledge from the data, but they often miss out some essential knowledge that can be easily captured in rule based systems.

    In this work, we address these challenges for poetry generation, which is one of the main areas of creative language generation. We introduce password poems as a new application for poetry generation. These passwords are highly secure, and we show that they are easier to recall and preferable compared to passwords created by other methods that guarantee the same level of security. Furthermore, we combine finite state machinery with deep learning models in a system for generating poems for any given topic. We introduce a quantitative metric for evaluating the generated poems and build the first interactive poetry generation system that enables users to revise system generated poems by adjusting style configuration settings like alliteration, concreteness and the sentiment of the poem. The system interface also allows users to rate the quality of the poem. We collect users rating for poems with various style settings and use them to automatically tune the system style parameters. In order to improve the coherence of generated poems, we introduce a method to borrow ideas from existing human literature and build a poetry translation system. We study how poetry translation is different from translation of noncreative texts by measuring the language variation added during the translation process. We show that humans translate poems much more freely compared to general texts. Based on this observation, we build a machine translation system specifically for translating poetry which uses language variation in the translation process to generate rhythmic and rhyming translations.

    Biography: Marjan Ghazvininejad is a Ph.D. student at ISI working with Professor Kevin Knight

    Host: Nanyun Peng

    More Info: http://nlg.isi.edu/nl-seminar/

    Location: Information Science Institute (ISI) - 11th Flr Conf Rm # 1135, Marina Del Rey

    Audiences: Everyone Is Invited

    Contact: Peter Zamar

    OutlookiCal