Juyang (John) Weng

A Short Technical Biography

Juyang (John) Weng received the BS degree in computer science from Fudan University, Shanghai, China, in 1982, and M. Sc. and PhD degrees in computer science from the University of Illinois at Urbana-Champaign, 1985 and 1989, respectively.

He was a faculty member of Computer Science and Engineering at Michigan State University, East Lansing, 1992-2021. He was also a faculty member of the Cognitive Science Program and the Neuroscience Program at Michigan State University. His research interests lie in the general area of natural intelligence and artificial intelligence, especially the autonomous development of a variety of mental capabilities by robots and animals, including perception, cognition, behaviors, motivation, and abstract reasoning skills. He has published over 300 peer-reviewed research articles on related subjects, including task muddiness, intelligence metrics, mental architectures, vision, audition, touch, attention, recognition, autonomous navigation, natural language understanding, and other emergent behaviors.

In 1992 and 1993, he published with N. Ahuja and T. S. Huang, the Cresceptron, whose journal version appeared in 1997. Cresceptron was inspired by Neocognitron. Neoconitron was for recognition of an individual character in a uniform background. Cresceptron appears to be the first visual learning program (now called deep learning network) for general objects in natural and cluttered background by directly taking inputs from sensors and effectors and producing outputs to effectors. It also does segmentation from a cluttered background. Since then, he has been concentrating on what is later called autonomous mental development, emphasizing autonomous generation of internal representation, including theories, methods and experimental studies.

He proposed a computational brain-mind model (Weng 2010) called Developmental Network (DN), which appears to be the first meant for the 5-chunk scale---development, architecture, area, space and time. He established (Weng 2011) that a Generative DN (GDN) can learn any given Turing Machine (TM) incrementally, immediately, and error-free. However, unlike the handcrafted TM, GDN is grounded in the physical world using emergent internal representations. This theoretical result bridges the well-known divide between symbolic representations and emergent representations in the sense that "neural networks do not abstract well" (Minsky 1991, also stated by Michael I. Jordan at the David Rumelhart Memorial Plenary Talk IJCNN 2011).

He authored the book,Naturnal and Artificial Intelligence (BMI Press, 1st edition 2012, 2nd edition 2019). He is a coauthor  (with T. S. Huang and N. Ahuja) of the book Motion and Structure from Image Sequences (Springer-Verlag, 1993). He is an Editor-in-Chief of International Journal of Humanoid Robotics and an associate editor of the IEEE Transactions on Autonomous Mental Development. He has chaired and co-chaired a few conferences, including the NSF/DARPA funded Workshop on Development and Learning 2000 (1st ICDL), 2nd International Conference on Development and Learning (ICDL 2002), 7th ICDL (2008), 8th ICDL (2009), and the INNS New Directions in Neural Networks Symposia (NNN 2008). He was the Chairman of the Governing Board of the International Conferences on Development and Learning (ICDLs) (2005-2007), founding 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.

 Back To Weng's Home Page: http://web.cps.msu.edu/~weng/