Byoung-Tak Zhang's Home Page

Byoung-Tak Zhang

	Professor School of Computer Science and Engineering & Cognitive Science, Brain Science, and Bioinformatics Seoul National University Seoul 151-744, Korea Office: Room 302-323 (New Engineering Building) Phone: +82-2-880-1833 (office), 880-1847 (secretary) Fax: +82-2-875-2240 E-mail: btzhang@bi.snu.ac.kr URL: http://bi.snu.ac.kr/~btzhang/

RESEARCH

Research Overview
My long-term research goal is (i) to understand the natural (biological and/or cognitive) information processing principles underlying human learning, memory, and intelligence, and (ii) to use these principles to develop innovative computational architectures and algorithms for building synthetic intelligence systems solving practical problems. This natural computation approach to machine learning and intelligence has, thus, aspects of both science and technology. I strive to address the problems based on real-life settings, and solve them using principled methods so that we make long-term progress in the advancement of technology.
My current research is centered around the hypernetwork model. It is a random hypergraph structure for learning higher-order probabilistic relationships from data. The model is inspired by biological networks that evolve via variation and selection at the molecular level. The working hypothesis in the hypernetwork approach to synthetic intelligence is that associative learning through massive interaction of a large number of memory units, like molecules in biological networks, is a foundational element for robust, flexible information processing and decision-making in human brain and other natural biological systems.
The research on hypernetworks has so far focused on developing the mathematical models and learning algorithms based on molecular evolutionary computation (MEC), i.e. evolutionary computation using molecules. In my group we work on novel applications and comparative analysis of the algorithms with other cutting-edge machine learning techniques. The hypernetwork models are also being implemented in electronic hardware and in vitro DNA computing. More details on these and related projects currently going on in my Biointelligence Laboratory can be found by visiting the pages:

Theory: Hypernetwork Models of Learning and Memory
Applications: Data Mining in Life Sciences and Life Blogs
Technology: Molecular Evolutionary Computation in Silico and in Vitro

Journal Editorship

IEEE Transactions on Evolutionary Computation, Associate Editor (1997-2010)
Applied Intelligence, Review Board Member
BioSystems, Associate Editor
Journal of Cognitive Science, Editorial Board Member
Genetic Programming and Evolvable Machines, Editorial Board Member
Advances in Natural Computation (Book Series), Associate Editor

Graduate Courses Taught

Cognitive Neural Computation (2013)
Action-Perception-Learning Cycles (2012)
Multisensory Predictive Learning (2011)
Dynamic Learning (2010)
Bayesian Cognition (2010)
Probabilistic Graphical Models (2009)
Cognitive Machine Learning (2008)
Hypernetwork Models of Learning and Memory (2006)
Information Theory of Learning (2005)
Molecular Machine Learning (2004)
Biomolecular Computation (2003)
Molecular Intelligence (2002)
Bioinformatics and Machine Learning (2001)
Intelligent Learning Agents (2000)
Statistical Learning Theory (1999)
Machine Learning (1998, 1997)

Talks and Tutorials

Position Papers & Monographs [Korean]

Meetings Organized

Selected Publications

Information-theoretic objective functions for lifelong learning, B.-T. Zhang, AAAI 2013 Spring Symposium on Lifelong Machine Learning, Stanford University, March 25-27, 2013. [PDF]
Sparse population code models of word learningin concept drift, B.-T. Zhang, J.-W. Ha, and M. Kang, In Proceedings of the 34th Annual Meeting of the Cognitive Science Society (CogSci 2012), 2012. [PDF]
A DNA assembly model of sentence generation, J.-H. Lee, S. H. Lee, W.-H. Chung, E. S. Lee, T. H. Park, R. Deaton, and B.-T. Zhang, BioSystems, 106:51-55, 2011. [PDF]
Hypernetworks: A molecular evolutionary architecture for cognitive learning and memory, B.-T. Zhang, IEEE Computational Intelligence Magazine, 3(3):49-63, August 2008.[PDF][LINK]
Molecular basis for the recognition of primary microRNAs by the Drosha-DGCR8 complex, J. Han, Lee Y, K.H. Yeom, J.-W. Nam, I. Heo, J.-K. Rhee, S. Y. Sohn, Y. Cho, B.-T. Zhang and V.N. Kim, Cell, 125:887-901, 2006. [PDF]
Multi-objective evolutionary optimization of DNA sequences for reliable DNA computing, S.-Y. Shin, I.-H. Lee, D. Kim, and B.-T. Zhang, IEEE Transactions on Evolutionary Computation, 9(2):143-158, 2005. [PDF]
Bayesian model averaging of Bayesian network classifiers over multiple node-orders: application to sparse datasets, K.-B. Hwang and B.-T. Zhang, IEEE Transactions on Systems, Man, and Cybernetics Part B: Cybernetics, 35(6):1302-1310, 2005. [PDF]
Self-organizing latent lattice models for temporal gene expression profiling, Zhang, B.-T, Yang, J. and Chi, S. W., Machine Learning, 52(1/2):67-89, 2003. [PDF]
System identification using evolutionary Markov chain monte carlo, Zhang, B.-T. and Cho, D.-Y., Journal of Systems Architecture, 47(7):587-599, 2001. [PDF]
Bayesian methods for efficient genetic programming, Zhang, B.-T., Genetic Programming and Evolvable Machines, 1(3):217-242, 2000. [PDF]
Evolutionary induction of sparse neural trees, Zhang, B.-T., Ohm, P., and Mühlenbein, H., Evolutionary Computation, 5(2):213-236, 1997. [PDF]
Balancing accuracy and parsimony in genetic programming, Zhang, B.-T. and Mühlenbein, H., Evolutionary Computation, 3(1):17-38, 1995. [PDF]
Accelerated learning by active example selection, Zhang, B.-T., International Journal of Neural Systems, 5(1):67-75, 1994. [PDF]
Evolving optimal neural networks using genetic algorithms with Occam's razor, Zhang, B.-T. and Mühlenbein, H., Complex Systems, 7(3):199-220, 1993. [PDF] [LINK]

[more]

Biointelligence Lab

School of Computer Sci. & Eng.

SNU