WCCI Wide Tutorial

Computational Brain-Mind:
From Biology, Neuroscience, Psychology, Computer Science, Electrical Engineering, and Mathematics



Top | Abstract | Instructor | Tutorial Topics | Biography of Instructor | Selected Publications | Brain-Mind Institute

Tutorial for WCCI 2012

Abstract

This tutorial will present material about the brain and mind (brain-mind) from the viewpoints of six disciplines --- biology, neuroscience, psychology (including cognitive science), computer science, electrical engineering, and mathematics.   However, any person with a undergraduate degree should be able to understand much of the material presented.   An overarching model about how the brain-mind works will be presented backed by evidence from the six disciplines.  The model proposes six necessary "chunks" for the brain-mind picture:  development, architecture, area, space, time and modulation.

The development chunk takes into account how biological cells autonomously migrate, grow, connect, adapt, and interact with one another need for us to understand not only how the brain works but also how the mind emerges.  

The architecture chunk describes how the biological development gives rise to connections and interactions among cerebral areas to give rise to the brain that neuroscience studies.   It explains organization principles for the functions of perception, cognition, motivation and behavior that psychology studies.  The architecture also outlines how the brain leans concepts, meanings, and procedures from the physical world; deals with multiple objects in complex backgrounds; self-generates intent; reasons with intent; and integrates multiple sensory and motor modalities.   These are subjects that computer science deals with but with great difficulties.

The area chunk addresses the issue of feature development and areal representation and how the role of each neuron emerges from interactions among cells in each area.  The representational optimality will be discussed,  in terms of the limited neuronal resource and the limited learning experience.   These issues are central for neural networks that electrical engineering and other disciplines deal with.

The space chunk clarifies how the brain network deals with spatial information, such as bottom-up and top-down attention (e.g., to deal with multiple objects in complex backgrounds), desired invariance (location invariance and type invariance), desired specificity (e.g., object type specificity and object location specificity), abstract concepts,  and meanings.  All the six disciplines are interested in these issues. 

The time chunk addresses how the brain uses its intrinsic spatial mechanisms to deals with time, without dedicated temporal components (e.g., silence detector or key frame detector), such as contexts of spatiotemporal events while having desired properties for time warping, time duration, temporal attention, and emergence of behaviors for any temporal length and any temporal subsets.   Again, all the six disciplines are interested in these issues. 

The modulation chunk clarifies the brain’s intrinsic motivational system so that the brain not only performs signal processing, but also be sensible to punishment, regards, and novelty.  We will discuss the serotonin system and the dopamine system, but only touch on the acetylcholine system and the norepinephrine system.  In addition to the six disciplines, medicine, social science, political sciences, and philosophy are interested in such subjects.

The theory, mechanisms and algorithms are presented with related experimental results. 

Instructor

Juyang (John) Weng, Professor
Embodied Intelligence Laboratory
Department of Computer Science and Engineering,
Cognitive Science Program, and Neuroscience Program
Michigan State University
East Lansing, MI 48824 USA
Tel: 517-353-4388, 617-253-8024
Email: weng@cse.msu.edu
http://www.cse.msu.edu/~weng/

Tutorial Topics

1.     Agent and a history of agent research

2.     Biological development: genes, mitosis, genomic equivalence, cell migration, cell signaling, morphogens and epigenesis.

3.     Symbolic representations and agent architectures, such as 2.5-D maps, optical flows, SLAM and SMPA framework.

4.     Symbolic contextual representations and argent architectures, such as Bayesian Net, HMM, MDP, POMDP, Kismet, Cog.

5.     Emergent spatial representations and architectures, such as Cresceptron, SOM, LVQ, LISSOM, ICA, LCA, LDA, SVM, SHOSLIF, HDR, AGREL and MILN

6.     Emergent temporal representations and architectures, such as Elman net, Jordan net, Hopfield net, Boltzman machines, LSTM, WSA, SASE, and DN.

7.     Early processing: receptors, retina, and LGN.

8.     Laminar architecture of all cerebral cortex, and its implications.

9.     Development of feature detectors in the laminar cortex.

10.  Architecture of the visuomotor streams, dorsal and ventral representation.

11.  Attention: bottom-up, top-down based on location, top-down based on type.

12.  Brain-like network-based reasoning, decision-making and planning.

13.  Space and time complexities of symbolic and emergent systems.

Length: 2 hours

Prerequisites:  General ideas about computer programs, basic knowledge about vectors.  

Audience: researchers and governmental scientific officials in biology, neuroscience, psychology (including cognitive science), signal processing, image processing, computer vision, pattern recognition, speech recognition, autonomous control, language processing, autonomous robots, human-machine interface, and artificial intelligence.

Handout: the WCCI 2012 organizing committee will provide tutorial material. 

Biographical Sketch of the Instructor

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 in 1982, his MS and PhD degrees from University of Illinois at Urbana-Champaign, 1985 and 1989, respectively, all in Computer Science.  From August 2006 to May 2007, he is also a visiting professor at the Department of Brain and Cognitive Science of MIT.   His research interests include computational biology, computational neuroscience, computational developmental psychology, biologically inspired systems, computer vision, audition, touch, behaviors, and intelligent robots.  He is the author or coauthor of over two hundred fifty research articles.  He is a Fellow of IEEE, an editor-in-chief of International Journal of Humanoid Robotics and an associate editor of the new IEEE Transactions on Autonomous Mental Development. He has chaired and co-chaired some conferences, including the NSF/DARPA funded Workshop on Development and Learning 2000 (1st ICDL), 2nd ICDL (2002), 7th ICDL (2008),  8th ICDL (2009), and INNS NNN 2008. He was the Chairman of the Governing Board of the International Conferences on Development and Learning (ICDLs) (2005-2007, http://cogsci.ucsd.edu/~triesch/icdl/), 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, an associate editor of IEEE Trans. on Image Processing.  

Selected Publications

J. Weng, N. Ahuja and T. S. Huang, “Learning recognition and segmentation using the Cresceptron,” International Journal of Computer Vision, vol. 25, no. 2, pp. 105-139, Nov. 1997.

D. L. Swets and J. Weng, “Hierarchical discriminant analysis for image retrieval,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 5, pp. 386 - 401, May 1999.

W. S. Hwang and J. Weng, “Hierarchical Discriminant Regression,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp. 1277 - 1293, Nov. 2000.

J. Weng, J. McClelland, A. Pentland, O. Sporns, I. Stockman, M. Sur and E. Thelen, “Autonomous Mental Development by Robots and Animals,” Science, vol. 291, no. 5504, pp. 599-600, Jan. 26, 2001. 

J. Weng and I. Stockman, “Autonomous Mental Development: Workshop on Development and Learning,” AI Magazine, vol. 23, no. 2, pp. 95-98, 2002. 

J. Weng, Y. Zhang and W. Hwang, “Candid Covariance-free Incremental Principal Component Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 8, pp. 1034-1040, 2003.

J. Weng, “Developmental Robotics: Theory and Experiments,” International Journal of Humanoid Robotics, vol. 1, no. 2, pp. 199-235, 2004.

J. Weng and W. Hwang, “From Neural Networks to the Brain: Autonomous Mental Development,” IEEE Computational Intelligence Magazine, vol. 1, no. 3, pp. 15-31, 2006.

J. Weng, “On Developmental Mental Architectures,” Neurocomputing, vol. 70, no. 13-15, pp. 2303-2323, 2007.

Y. Zhang and J. Weng, “Task Transfer by a Developmental Robot,” IEEE Transactions on Evolutionary Computation, vol. 11, no. 2, pp. 226-248, 2007. 

X. Huang and J.Weng, “Inherent Value Systems for Autonomous Mental Development,” International Journal of Humanoid Robotics, vol. 4, no. 2, pp. 407-433, 2007.

J. Weng, T. Luwang, H. Lu, X. Xue, “Multilayer In-place Learning Networks for Modeling Functional Layers in the Laminar Cortex,” Neural Networks, vol. 21, no.2-3, pp. 150-159, 2008.

Z. Ji, J. Weng and D. Prokhorov, “Where-What Network 1: ‘Where’ and ‘What’ Assist Each Other Through Top-down Connections,” IEEE International Conference on Development and Learning, Monterey, CA, pp. 61-66, Aug. 9-12, 2008.

J. Weng, “Task Muddiness, Performance Metrics and the Necessity of Autonomous Mental Development,” Minds and Machines, vol. 19, pp. 93-115, 2009.

J. Weng and M. Luciw, “Dually Optimal Neuronal Layers: Lobe Component Analysis,” IEEE Transactions on Autonomous Mental Development, vol. 1, no. 1, pp. 68-85, 2009.

Y. Zhang and J. Weng, “Spatiotemporal Multimodal Developmental Learning,” IEEE Transactions on Autonomous Mental Development, vol. 2, no. 3, pp. 149-166, 2010.

M. Luciw and J. Weng, “Where What Network 3:  Developmental Top-Down Attention with Multiple Meaningful Foregrounds,” in Proc. International Joint Conference on Neural Networks, Barcelona, Spain, pp. 4233-4240, July 18-23, 2010.

K. Miyan and J. Weng, “WWN-Text: Cortex-Like Language Acquisition with ’What’ and ’Where’,” in Proc. IEEE 9th International Conference on Development and Learning,'' Ann Arbor, pp. 280-285, August 18-21, 2010.

Top | Abstract | Instructor | Tutorial Topics | Biography of Instructor | Selected Publications | Brain-Mind Institute

 Back To Weng's Home Page: http://www.cse.msu.edu/~weng/