Search
mlsplogo MLSP2015
IEEE International Workshop on
Machine Learning for Signal Processing

September 17-20, 2015  Boston, USA

Deep learning and its applications in image and video analysis
Yu Kong Postdoc Yu Kong
Department of Electrical and Computer Engineering
Northeastern University, Boston, USA
Personal homepage

Biography:

Dr. Yu Kong received B.Eng. degree in automation from Anhui University in 2006, and PhD degree in computer science from Beijing Institute of Technology, China, in 2012. He was a visiting student at the National Laboratory of Pattern Recognition (NLPR), Chinese Academy of Science from 2007 to 2009, and visited the Department of Computer Science and Engineering, State University of New York, Buffalo in 2012. He is now a postdoctoral research associate in the Electrical and Computer Engineering, Northeastern University, Boston, MA. Dr. Kong's research interests are computer vision, social media analytics, and machine learning.

Yun Fu Professor Yun Fu
Department of Electrical and Computer Engineering
Northeastern University, Boston, USA

Personal homepage

Biographies:

Dr. Yun Fu received the B.Eng. degree in information engineering and the M.Eng. degree in pattern recognition and intelligence systems from Xi'an Jiaotong University, China, respectively, and the M.S. degree in statistics and the Ph.D. degree in electrical and computer engineering from the University of Illinois at Urbana-Champaign, respectively. Prior to joining the Northeastern faculty, he was a tenure-track Assistant Professor of the Department of Computer Science and Engineering, State University of New York, Buffalo, during 2010-2012. His research interests are Machine Learning, Computer Vision, Social Media Analytics, and Big Data Mining. He has extensive publications in leading journals, books/book chapters and international conferences/workshops. He serves as associate editor, chairs, PC member and reviewer of many top journals and international conferences/workshops. He is the recipient of 5 best paper awards (SIAM SDM 2014, IEEE FG 2013, IEEE ICDM-LSVA 2011, IAPR ICFHR 2010, IEEE ICIP 2007), 3 young investigator awards (2014 ONR Young Investigator Award, 2014 ARO Young Investigator Award, 2014 INNS Young Investigator Award), 2 service awards (2012 IEEE TCSVT Best Associate Editor, 2011 IEEE ICME Best Reviewer), etc. He is currently an Associate Editor of the IEEE Transactions on Neural Networks and Leaning Systems (TNNLS), and IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). He is a Lifetime Member of ACM, AAAI, SPIE, and Institute of Mathematical Statistics, member of INNS and Beckman Graduate Fellow during 2007-2008.

Abstract:

In the past 10 years, deep learning has gained growing interests in machine learning and computer vision due to its ability of learning highly discriminative and expressive features. Convolutional neural networks and stacked auto-encoder are two popular deep networks. They have shown promising results in image and video understanding. In this tutorial, we will first discuss the basic principles behind these two networks. Afterwards, we will show several applications using convolutional neural networks and stacked auto-encoder, including image understanding, face recognition, action recognition, and video recommendation. The objective of this tutorial is to overview recent progress in deep learning and its applications, as well as to discuss, motivate and encourage future research in image and video analysis using deep learning.

A Bayesian Perspective on the Design of EEG-based Brain-Computer Interfaces for Augmentative and Alternative Communication and Control
Murat Akcakaya Professor Murat Akcakaya
Electrical and Computer Engineering Department
University of Pittsburgh, USA

Personal homepage

Biography:

Murat Akcakaya received his B.Sc. in Electrical and Electronics Engineering from Middle East Technical University in Ankara, Turkey, in 2005, and his M.Sc. and the Ph.D degrees in Electrical Engineering from Washington University in St. Louis, in May and December 2010, respectively. He is currently an Assistant Professor in the Electrical and Computer Engineering Department of the University of Pittsburgh. His research interests include statistical signal processing and machine learning with applications to noninvasive electroencephalography (EEG) based brain-computer interface (BCI) systems, array signal processing, and physiological signal analysis for health informatics. Dr. Akcakaya was the winner of the student paper contest awards at the 2010 IEEE Radar Conference; the 2010 IEEE Waveform Diversity and Design Conference; and the 2010 Asilomar Conference on Signals, Systems and Computers. He has published his work in leading engineering journals and conferences.

Abstract:

Electroencephalography (EEG)-based brain-computer interfaces (BCIs) promise to provide a novel access channel for assistive technologies, including augmentative and alternative communication, and control of external devices for people with severe speech and physical impairments (SSPI). Research on the subject has been accelerating significantly in the last decade and the research community has taken great strides toward making EEG-based BCI a practical reality for individuals with SSPI. Nevertheless, there is much work to be done to produce viable systems that can be comfortably, conveniently, and reliably used by individuals with SSPI. This tutorial will describe a Bayesian approach for the design of an EEG-based BCI. A dynamic graphical model will be developed to model the temporal dependencies in EEG, to design a decision fusion model for intent inference, and to design adaptive optimum stimuli subset selection schemes. RSVP Keyboard™, a language model assisted EEG-based letter-by-letter typing system will be used as the testbed to demonstrate the design methodology.

Powered by CONWIZ, © Copyright 2014. Page maintained by Jan Larsen (Email)