Select a calendar:
Filter January Events by Event Type:
Events for January 22, 2016
-
AI Seminar
Fri, Jan 22, 2016 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Yisong Yue, Cal Tech
Talk Title: A Decision Tree Framework for Data-Driven Speech Animation
Abstract: n many animation projects, the animation artist typically spends significant time animating the face, which involves many labor-intensive tasks that offer little potential for creative expression. One particularly tedious task is speech animation: animating the face to match spoken audio. Indeed, the often prohibitive cost of speech animation has limited the types of animations that are feasible, including localization to different languages.
In this talk, I will show how to view speech animation through the lens of data-driven sequence prediction. In contrast to previous sequence prediction settings, speech animation is an instance of contextual spatiotemporal sequence prediction, where the output is continuous and high-dimensional (e.g., a configuration of the lower face), and also depends on an input context (e.g., audio or phonetic input).
I will present a decision tree framework for learning to generate context-dependent spatiotemporal sequences given training data. This approach enjoys several attractive properties, including ease of training, fast performance at test time, and the ability to robustly tolerate corrupted training data using a novel latent variable approach. I will showcase this approach in a case study on speech animation, where our approach outperforms several competitive baselines in both quantitative and qualitative evaluations, and also demonstrates strong robustness to corrupted training data.
This is joint work with Taehwan Kim, Sarah Taylor, Barry-John Theobald, and Iain Matthews.
Biography: Yisong Yue is an assistant professor in the Computing and Mathematical Sciences Department at the California Institute of Technology. He was previously a research scientist at Disney Research. Before that, he was a postdoctoral researcher in the Machine Learning Department and the iLab at Carnegie Mellon University. He received a Ph.D. fromCornell University and a B.S. from the University of Illinois at Urbana-Champaign.
Yisong's research interests lie primarily in the theory and application of statistical machine learning. He is particularly interested in developing novel methods for spatiotemporal reasoning, structured prediction, interactive learning systems, and learning with humans in the loop. In the past, his research has been applied to information retrieval, recommender systems, text classification, learning from rich user interfaces, analyzing implicit human feedback, data-driven animation, sports analytics, policy learning in robotics, and adaptive routing & allocation problems.
Host: Ashish Vaswani
More Info: http://webcasterms1.isi.edu/mediasite/SilverlightPlayer/Default.aspx?peid=6147027e077e4570919a58730193abf91d
Location: Information Science Institute (ISI) - 11th floor large conference room
Audiences: Everyone Is Invited
Contact: Kary LAU
Event Link: http://webcasterms1.isi.edu/mediasite/SilverlightPlayer/Default.aspx?peid=6147027e077e4570919a58730193abf91d
-
W.V.T. Rusch Engineering Honors Program Colloquium
Fri, Jan 22, 2016 @ 01:00 PM - 01:50 PM
USC Viterbi School of Engineering, Viterbi School of Engineering Student Affairs
University Calendar
Join us for a presentation by Prof. Greg Autry, from the University of Southern California, titled "Entrepreneurship in the New Space Industry."
Location: Seeley G. Mudd Building (SGM) - 101
Audiences: Everyone Is Invited
Contact: Ramon Borunda/Academic Services
-
EE-EP Seminar, Jae-Sun Seo, Friday, January 22nd at 2:00pm in EEB 132
Fri, Jan 22, 2016 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Jae-sun Seo, Arizona State University
Talk Title: Designing Power-Efficient Neuromorphic VLSI Systems That Can Learn and Infer
Abstract: In recent years, both industry and academia have shown large interest in low-power hardware designs for neuromorphic computing (e.g. TrueNorth) and machine learning algorithms (e.g. convolutional neural networks) for a wide range of image, speech, and biomedical applications. State-of-the-art algorithms are computation-/memory-/communication-intensive, however, making it difficult to perform low-power real-time training and classification. Furthermore, to optimize system-level power, efficient power delivery and voltage regulation of such VLSI systems also becomes a critical concern.
In this talk, I will present our exemplary research on low-power digital neuromorphic processor design with on-chip learning, as well as workload-adaptive integrated voltage regulators. I will discuss our work on on-chip STDP (spike-timing dependent plasticity) learning for pattern recognition (45nm), spiking clustering for deep-brain sensing (65nm), and a versatile neuromorphic processor design that can support various STDP learning / inhibition rules found in neuroscience literature with large fan-in/out per neuron. To provide an efficient and stable power supply for such processors against fluctuating workloads, integrated switched-capacitor voltage regulator designs are proposed with fast on-chip current sensing (32nm) and capacitance dithering (65nm).
I will also briefly discuss our machine learning hardware designs for speech and biometric applications, and present future research directions to vertically integrate and further improve the power-efficiency of neuromorphic systems while bridging the gap with machine learning approaches.
Biography: Jae-sun Seo received his Ph.D. degree from the University of Michigan in 2010 in electrical engineering. From 2010 to 2013, he was with IBM T. J. Watson Research Center, where he worked on neuromorphic chip design for the DARPA SyNAPSE project and energy-efficient circuits for IBM's high-performance processors. Since January 2014, he has been with Arizona State University as an assistant professor in the School of ECEE. During the summer of 2015, he was a visiting faculty at Intel Circuits Research Lab. His research interests include efficient hardware design of learning algorithms and integrated power management. He received the IBM outstanding technical achievement award in 2012, and serves on the technical program committee for ISLPED and the organizing committee for ICCD.
Host: EE-EP
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
-
NL Seminar-EXTRACTING USER INFORMATION FROM ONLINE SOCIAL MEDIA
Fri, Jan 22, 2016 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Jiwei Li, Stanford University
Talk Title: EXTRACTING USER INFORMATION FROM ONLINE SOCIAL MEDIA
Series: Natural Language Seminar
Abstract: The overwhelming popularity of online social media creates an unprecedented opportunity to display aspects of oneself. Inferring information about these users has the potential to benefit many downstream applications such as recommendation engines and targeted advertising. In this talk I will show how to extract important personal information such as major life events and personal attributes (e.g., gender, education, job) from social evidence such as the text produced by users and their friends and from properties of their social network. I will describe algorithms making use of a variety of frameworks, including distant supervision, and a deep learning architecture that learns user representations by integrating many heterogeneous social signals.
Biography: Jiwei Li is a PH.D. student in the computer science department at Stanford University, working with Prof. Dan Jurafsky. His research interests include discourse, language generation, and social networks, with a focus on deep learning methods. Jiwei receives his B.S. from Peking University in 2012. He was rewarded the Facebook Fellowship in 2015.
Host: Xing Shi and Kevin Knight
More Info: http://nlg.isi.edu/nl-seminar/
Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=6b5348f2f8dc4a4dbb595eca444410d51dLocation: Information Science Institute (ISI) - 6th Flr Conf Rm # 689, Marina Del Rey
WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=6b5348f2f8dc4a4dbb595eca444410d51d
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
-
Astani Civil and Environmental Engineering Ph.D. Seminar
Fri, Jan 22, 2016 @ 03:00 PM - 04:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Yoichi Mukai Associate Professor, Dr.Eng. , Department of Architecture, Kobe University
Talk Title: Introduction of the real-time hybrid simulator with shaking-table in Kobe University
Abstract:
Dr. Mukai's research group has been interested in re-assessment of existing buildings and re-evaluation of traditional and historical structures. For this purpose, we are researching about development of practical techniques for sounding of damaged building conditions or for evaluation and estimation of structural mechanism of traditional structures, through monitoring and sensing techniques. Dr. Mukai's research group is currently developing a real-time hybrid simulator for investigating structural response control systems with semi-active-active control devices. This activity, to develop the real-time hybrid simulator, are carried out by the collaboration with Prof. Fujitani & Dr. Ito's research group, mainly researching on development of advanced seismic-isolation system with semi-active controlling dampers retrofit for high-rise building structures with newly proposing slit-inserted steel plate dampers, etc. The real-time hybrid simulator is actualized by installing real-time response generator of the inside numerical model as the additional function on the actual shaking-table. We make the shaking-table generate interactive movement between the inside numerical model and the actual external specimen devices. This system can be exactly simulate computed interaction movement, so we can operate hybrid experimental test of whole structural system by connecting vertically the actual specimen to the internal model while we don't need to prepare in whole the structural system but to prepare limited part only which we actually focus on and want to know its behavior in detail.
"Image Based Detection for Concrete Fracture"
Tomohiro Miki Associate Professor, Dr.Eng.
Department of Civil Engineering, Kobe University
Host: Dr, Maria Todorovska
Location: Seeley G. Mudd Building (SGM) - 101
Audiences: Everyone Is Invited
Contact: Evangeline Reyes