Events for the 3rd week of April
-
Emerging Trends Seminar Series
Mon, Apr 10, 2017 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: C.C. Jay Kuo, Dean's Professor of Electrical Engineering, Ming Hsieh Department of Electrical Engineering
Talk Title: CNN as Guided Multi-layer RECOS Transform
Series: Emerging Trends
Abstract: There is a resurging interest in developing a neural network based solution to supervised machine learning in the last 5 years. In this talk, I will provide a theoretical foundation to the working principle of the convolutional neural network (CNN) from a signal processing viewpoint. To begin with, the RECOS transform is introduced as a basic building block for CNNs.
The term RECOS is an acronym for REctified-COrrelations on a Sphere. It consists of two main concepts: data clustering on a sphere and rectification. Then, a CNN is interpreted as a network that implements the guided multilayer RECOS transform. Along this line, we first compare the traditional single-layer and modern multilayer signal analysis approaches. Then, we discuss how guidance is provided by data labels through back propagation in the training with an attempt to offer a smooth transition from weakly to heavily supervised learning. Finally, we show that a trained network can be greatly simplified in the testing stage, which demands only one bit representation for both filter weights and inputs. Several future research directions are pointed out at the end.
Biography: Dr. C.C. Jay Kuo received his Ph.D. degree from the Massachusetts Institute of Technology in 1987. He is now with the University of Southern California (USC) as Director of the Media Communications Laboratory and Dean's Professor in Electrical Engineering, Systems. His research interests are in the areas of digital media processing, compression, communication and networking technologies. Dr. Kuo was the Editor in Chief for the IEEE Trans. on Information Forensics and Security from 2012 through 2014. He was the Editor in Chief for the Journal of Visual Communication and Image Representation from 1997 through 2011, and served as Editor for 10 other international journals.
Dr. Kuo received the 1992 National Science Foundation Young Investigator (NYI) Award, the 1993 National Science Foundation Presidential Faculty Fellow (PFF) Award, the 2010 Electronic Imaging Scientist of the Year Award, the 2010-11 Fulbright-Nokia Distinguished Chair in Information and Communications Technologies, the 2011 Pan Wen Yuan Outstanding Research Award, the 2014 USC Northrop Grumman Excellence in Teaching Award, the 2016 USC Associates Award for Excellence in Teaching, the 2016 IEEE Computer Society Taylor L. Booth Education Award, the 2016 IEEE Circuits and Systems Society John Choma Education Award, the 2016 IS&T Raymond C. Bowman Award, and the 2017 IEEE Leon K. Kirchmayer Graduate Teaching Award. Dr. Kuo is a Fellow of AAAS, IEEE and SPIE. He has guided 140 students to their Ph.D. degrees and supervised 25 postdoctoral research fellows. Dr. Kuo is a co author of about 250 journal papers, 900 conference papers, 14 books and 30 patents.
Host: Ming Hsieh Institute
More Info: https://www.facebook.com/events/1444859602200671/
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Cathy Huang
Event Link: https://www.facebook.com/events/1444859602200671/
-
Center for Cyber-Physical Systems and Internet of Things and Ming Hsieh Institute for Electrical Engineering Joint Seminar Series on Cyber-Physical Systems
Mon, Apr 10, 2017 @ 03:00 PM - 04:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Natalie Cheung , Intel
Talk Title: Utilizing Drones to Create a New Nighttime Entertainment
Abstract: Come learn how Intel is utilizing drones in a different way -“ to light up the sky in a choreographed aerial performance with the Intel Drone Light Show. You'll learn about the Intel Shooting Star Drone, the technology behind the show, and more.
Biography: Natalie Cheung is the General Manager for the Drone Light Show in the UAV Group at Intel Corporation. She is responsible for establishing the drone light show business and growing the new segment. Cheung has led drone light show collaborations with customers that created activations across the globe - from the US, Germany, Mexico, Australia, and more.
Prior to her current role, Cheung was the Drone Marketing Director. She was responsible for product launches, conferences and events, and building awareness within the drone segment. Cheung has also served as Drone Product Manager, Research Analyst for Intel CEO Brian Krzanich. Cheung joined Intel in 2011. She earned a bachelor's and master's degree in electrical engineering and computer science from Massachusetts Institute of Technology.
Host: Paul Bogdan
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Estela Lopez
-
MHI CommNetS Seminar
Wed, Apr 12, 2017 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Ian M. Mitchell, University of British Columbia
Talk Title: Using model checking verifications online: Handling runtime state uncertainty, human-in-the-loop shared control and sampled data feedback
Series: CommNetS
Abstract: Recent advances in model checking algorithms for continuous state systems allow us to demonstrate the existence of safe control policies robust to model error for cyber-physical systems (CPS) of practical interest, such as shared control drones or wheelchairs, or automated delivery of anesthesia. However, these verification results are only relevant if we can implement those policies. In this talk I will discuss investigations into three challenges that arise when it comes time to synthesize a feedback control signal that will keep the system safe: Online state uncertainty, human-in-the-loop shared control for older adults with cognitive impairment, and the sampled data nature of that feedback control in typical cyber-physical systems.
Biography: Ian M. Mitchell completed his doctoral work in engineering at Stanford University in 2002, spent a year as a postdoctoral researcher at the University of California at Berkeley, and is now an Associate Professor of Computer Science at the University of British Columbia. He is the author of the Toolbox of Level Set Methods, the first publicly available high accuracy implementation of solvers for dynamic implicit surfaces and the time dependent Hamilton-Jacobi equation that works in arbitrary dimension. His research interests include development of algorithms and software for nonlinear differential equations, formal verification, control and planning in cyber-physical and robotic systems, assistive technology and reproducible research.
Host: Prof. Insoon Yang
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Annie Yu
-
Jelena Vuckovic - Munushian Seminar, Friday, April 14th at 2:00pm in EEB 132
Fri, Apr 14, 2017 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Jelena Vuckovic, Stanford University
Talk Title: Quantum Nanophotonics
Abstract: Nanophotonic structures that localize photons in sub-wavelength volumes are possible today thanks to modern nanofabrication and optical design techniques. Such structures enable studies of new regimes of light-matter interaction, quantum and nonlinear optics, and new applications in computing, communications, and sensing. While the traditional quantum nanophotonics platform is based on quantum dots inside photonic crystal cavities, recently a lot of progress has been made on systems consisting of color centers in diamond and silicon carbide, which could potentially bring these experiments to room temperature and facilitate scaling to large networks of resonators and emitters. Moreover, the use of inverse nanophotonic design methods, that can efficiently perform physics-guided search through the full parameter space, leads to optical devices with properties superior to state of the art, including smaller footprints, better field localization, and novel functionalities.
Biography: Jelena Vuckovic (PhD Caltech 2002) has been a faculty at Stanford since 2003, where she is currently a Professor of Electrical Engineering and by courtesy of Applied Physics, and where she leads the Nanoscale and Quantum Photonics Lab. She has also held visiting positions at the Humboldt University in Berlin, Germany, and the Technical University in Munich, Germany. Vuckovic is a recipient of numerous awards, including the Humboldt Prize, the Hans Fischer Senior Fellowship, and the Presidential Early Career Award for Scientists and Engineers (PECASE). She is a Fellow of the American Physical Society (APS) and of the Optical Society of America (OSA), and a member of the scientific advisory board of the Max Planck Institute for Quantum Optics (MPQ) in Munich, Germany.
Host: EE-Electrophysics
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski