Brain-Inspired Emergent Universal Turing Machines for Intention, Computer Vision, Audition and Natural Languages

Thời gian bắt đầu: 12:00 am 08/03/2019

Thời gian kết thúc: 12:00 am 08/03/2019

Địa điểm: P.803 - Nhà B1 - Đại học BKHN

Thời gian: 14.30 ngày 8/3/2019

Địa điểm: phòng 803 B1, Đại học Bách khoa Hà Nội

Người trình bày: Prof. Juyang (John) Weng, Department of Computer Science and Engineering, Cognitive Science Program, and Neuroscience Program, Michigan State University

Dr. Weng with his research group has made major advances in understanding and modeling how human brains learn and work, through theory, algorithms, and experimental demonstrations.   In this introductory talk, Dr. Weng will outline how a new kind of neural network, Developmental Network (DN), models how a human brain learns vision, audition, and natural languages throughout lifetime.  In particular, the theory explains how distributed neuronal representations automatically emerge and update inside the brain skull.  This emergence takes place while the human body is interacting with the physical world using sensors and effectors.  The human teachers outside the brain skull can see that the learner brain becomes increasingly capable of doing a series of open-ended tasks, from simple tasks as a baby to complex tasks as an adult.   Contrary to many AI researchers who still think that neural networks can do pattern recognition only, the DN automatically learns a general-purpose computer (i.e., emergent universal Turing Machine).  This is significant because the universal Turing machine is a well-accepted model for all general-purpose computers.  The talk will use stereo vision as an example to explain how the DN learn detecting objects, recognizing objects, estimating how far each object is, as it is taught or it wants.

Short Bio:

Juyang (John) Weng is a professor at the Department of Computer Science and Engineering, the Cognitive Science Program, and the Neuroscience Program, Michigan State University, East Lansing, Michigan, USA. He received his BS degree from Fudan University, China, in 1982, his MS and PhD degrees from University of Illinois at Urbana-Champaign, USA, 1985 and 1989, respectively, all in Computer Science.  From August 2006 to May 2007, he was also a visiting professor at the Department of Brain and Cognitive Science of MIT, USA.   Cresceptron by Drs. J. Weng, N. Ahuja, and T. S. Huang published 1992 was the first deep learning neural network for 3D natural world.  It seeded the current deep learning wave in artificial intelligence (AI).  His research interests include brain models, computational neuroscience, computational developmental psychology, computer vision, audition, touch, natural languages, and intelligent robots.  He is the author or coauthor of over three hundred research articles. He is an editor-in-chief of International Journal of Humanoid Robotics, the editor-in-chief of the Brain-Mind Magazine, and an associate editor of the new IEEE Transactions on Autonomous Mental Development (now IEEE Transactions on Cognitive and Developmental Systems). He was the Chairman of the Governing Board of the International Conferences on Development and Learning (ICDLs) (2005-2007,, chairman of the Autonomous Mental Development Technical Committee of the IEEE Computational Intelligence Society (2004-2005), an associate editor of IEEE Trans. on Pattern Recognition and Machine Intelligence, and an associate editor of IEEE Trans. on Image Processing.  He is a Fellow of IEEE.

Kính mời quý vị quan tâm tham dự.