返回主页

《计算认知与神经发育》课程相关信息

《计算认知与神经发育》课程简介

 

《计算认知与神经发育》课程相关信息

http://www.cs.fudan.edu.cn/dragonstar/

《计算认知与神经发育》课程简介

 

Computational Cognitive and Neural Development

 

Lecturer:

Juyang Weng (翁巨扬), Professor

Department of Computer Science and Engineering

Michigan State University

East Lansing, MI 48824

USA

http://www.cse.msu.edu/~weng/

 

Abstract

 

Mental development is an autonomous, open-ended process during which an agent (human or machine) interacts with its environment (including humans) through its life span, guided by what is called the developmental program (i.e., the genome or an equivalent).    A major difference between traditional programs and a developmental program is that the latter is not task-specific, i.e., the tasks that the agent will learn are unknown or not fully predictable during the programming (or birth) time.   There is no lack of computational models that characterize the computational architecture of the brain at different degrees of detail.   However, there is a lack of architecture models that incorporate perceptual signal processing, cognitive (logic) processing, and the developer of the processors.   Understanding properties of mental architectures is of fundamental importance for understanding neural processing systems, their adaptation and developmental learning.

 

This lecture systematically reviews key properties of mental architecture using existing major studies and models as examples, including perceptual architectures (e.g., Neisser’s  two stage visual processing scheme; Feldman & Ballard’s 100-step rule; John Tsotsos' model of immediate vision, HMM models), cognitive architectures (e.g., Soar proposed by Laird, Newell & Rosenbloom, ACT-R by Anderson, and the architecture outline by Albus), motor architectures (e.g., the subsumption architecture by Rodney Brooks and others), value system architectures (e.g., reinforcement learning, Q-learning, and other recent more complete models).   Based on recent results from neural science, psychology and computational intelligence, this tutorial further explain a series of properties for higher biological mental architectures along with the corresponding architecture components.   Architecture examples are used to illustrate such architecture properties.   The series of architectural theory explains how a neural system that does not contain any pre-defined symbolic internal representation can be autonomously developed (through programming, prenatal growth and postnatal experience from environment) to deal with not only perceptual tasks such as recognition and classification, but also sensor-driven higher cognitive tasks, such as abstraction, logical reasoning, thinking, planning, and language acquisition and understanding. 

    

Tutorial topics:

 

1.      Biological body development and mental development

2.      The history of biologically motivated architectures

3.      Review of animal learning theories, nonassociative and associative learning, classical conditioning, instrumental conditioning, time sequence learning, cognitive learning

4.      The brain, the cortex, and the cortical laminar architecture

5.      Supervised, reinforcement, communicative learning, and the refined 8 learning types

6.      Perceptual processing: retina, LGN, visual cortex as visual processing examples

7.      Cognitive processing: recognition, classification, and invariance

8.      Motor processing: rehearsal and coupling of effectors

9.      Sensorimotor pathways and their development

10.  Motivational system: limbic system, intention, value, and their development

11.  A hierarchy of mental architectures: non-observation-driven, observation-driven, attention selective, rehearsable, self-aware and self-effecting, developmental, multi-level

12.  Example architectures and experimental studies

 

Prerequisites:  General programming experience, basic knowledge about vector and matrix operations.  

Audience:  researchers in biological neural systems, signal processing, image processing, computer vision, pattern recognition, speech recognition, autonomous navigation, autonomous control, language processing, robotics, human-machine interface, and artificial intelligence.

 

Handout: Tutorial material will be provided by the host institution. 

 

Biographical sketch of the lecturer:

Juyang (John) Weng received his BS degree from Fudan University January 1982, MS and PhD degrees from University of Illinois at Urbana Champaign, May 1985 and January 1989, respectively, all in computer science.   He is now a professor at the Department of Computer Science and Engineering, Michigan State University, East Lansing, Michigan, USA.   His research interests include biologically inspired neural systems and their development, vision, audition, touch, human-machine multimodal interface, and intelligent robots. He initiated and supervised the SAIL (Self-organizing Autonomous Incremental Learner) and Dav projects, in which he and his coworkers have designed and custom built their SAIL and Dav robots for research on autonomous mental development. He is the author or coauthor of over two hundred research articles and book chapters.  He is an editor-in-chief of International Journal of Humanoid Robotics and the Chairman of the ICDL Governing Board.  He was the chairman of the Autonomous Mental Development Technical Committee of the IEEE Computational Intelligence Society, an associate editor of IEEE Trans. on Pattern Recognition and Machine Intelligence, an associate editor of IEEE Trans. on Image Processing, a program co-chair of the NSF/DARPA Workshop on Development and Learning (WDL), held April 2000 at Michigan State University (MSU), East Lansing, MI (http://www.cse.msu.edu/dl/), and a program co-chair of the International Conference on Development and Learning 2002 (ICDL’02), held at Massachusetts Institute of Technology, Cambridge, MA, June 2002 (http://www.egr.msu.edu/icdl02/).  His home page is at http://www.cse.msu.edu/~weng/.