VASANT HONAVAR

VASANT HONAVAR
Associate Professor
Artificial Intelligence Research Laboratory
Department of Computer Science
210 Atanasoff Hall
Iowa State University
Ames, Iowa 50011-1040
voice: (515) 294-1098
fax: (515) 294-0258
email: honavar@cs.iastate.edu

On Sabbatical at Carnegie Mellon University School of Computer Science from September 1 through December 31, 1998.

Contact address: Vasant Honavar, Visiting Professor, Computer Science Department, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213-3891. honavar+@cs.cmu.edu

You can generally find me here.

• Professional
  • Brief Biographical Sketch
  • The Formative Years
  • Current Affiliations
  • Research and Teaching Interests
  • Research Overview and Selected Publications
  • Books
  • Current and Former Graduate Students
  • Teaching
  • Professional Activities
  • Semester Schedule
  • Artificial Intelligence Research Laboratory
  • Publications
  • Advice on Graduate Studies, Research, and Careers in Computer Science
  • Other Useful Links
• Personal
  • Interests and Hobbies
  • Favorite Quotations

Vasant Honavar received his Ph.D. in Computer Science and Cognitive Science from the University of Wisconsin (Madison) in 1990. He joined the Department of Computer Science at Iowa State University in 1990 where he is presently an associate professor. He is also on the faculty of the Interdepartmental Graduate Program in Neuroscience.

Honavar's current research and teaching interests include: artificial intelligence, cognitive science, machine learning, neural networks, intelligent agents, and multi-agent systems, adaptive systems, data mining and knowledge discovery, computational and cognitive neuroscience, evolutionary computation and artificial life, machine perception, intelligent manufacturing systems, intelligent systems, knowledge-based systems, robotics, pattern recognition, medical informatics, intelligent multi-media information systems and artificial intelligence applications in science and engineering, and parallel and distributed computing.

Honavar founded and directs the Artificial Intelligence Research Laboratory in the Department of Computer Science at Iowa State University. Some of the research in this laboratory has been supported through research grants from National Science Foundation, John Deere Foundation, Carver Foundation, National Security Agency, and Iowa State University, as well as fellowships and research assistantships funded by the IBM Corporation, and the Iowa State University Graduate College.

Honavar has published over 70 refereed papers in journals and conferences and 10 invited book chapters on these topics. He has also edited three books: Artificial Intelligence and Neural Networks: Steps Toward Principled Integration (with Prof. Leonard Uhr), published by Academic Press in 1994; Grammatical Inference (Lecture Notes in Computer Science Vol. 1433) (with Giora Slutzki) published by Springer-Verlag in 1998; Advances in Evolutionary Synthesis of Neural Systems (with Mukesh Patel) to be published by MIT Press in 1998. He is writing a book (with Dr. Ron Sun and Dr. Charles Ling) on Adaptive and Learning Systems.

Honavar has served on program committees of numerous conferences, the most recent ones being World Congress on Neural Networks (WCNN), the International Conference on Machine Learning (ICML), and the Genetic Programming Conference (GP). He has organized several workshops, the most recent being the Workshop on Automata Induction, Grammatical Inference, and Language Acquisition held in conjunction with ICML 97. He is the program chairperson for the Fourth International Colloquium on Grammatical Inference to be held at Iowa State University in Ames in July 1998.

Honavar is an editor-in-chief of the Journal of Cognitive Systems Research which will be published by Elsevier starting in January 1999. He is an editor (with Colin de la Higuera) of a special issue of the Machine Learning journal on automata induction, grammar inference, and language acquisition. Honavar serves as a referee for several journals including IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Expert, Connection Science, IEEE Transactions on Evolutionary Computation, IEEE Transactions on Neural Networks, Neural Computation, Information Sciences, IEEE Transactions on Knowledge and Data Engineering, Applied Intelligence, Evolutionary Computation, Machine Vision and Applications, Connection Science, Microcomputer Applications, and Neural Networks.

Honavar has designed and taught graduate and undergraduate courses in Artificial Intelligence, Machine Learning, Neural Networks, Intelligent Agents and Multi-Agent Systems, and seminars in Cognitive and Neural Modeling, Data Mining and Knowledge Discovery, and Evolutionary Computation, Complex Adaptive Systems, and related topics. He has developed and presented tutorials on several topics in Machine Learning, the most recent one being a Tutorial on Computational Learning Theory at the 1997 Genetic Programming Conference at Stanford University.

Honavar is a member of Institution of Electrical and Electronics Engineers (IEEE), Association for Computing Machinery (ACM), American Association of Artificial Intelligence (AAAI), Cognitive Science Society, Society for Neuroscience, Neural Network Society, New York Academy of Sciences, and Sigma Xi and an associate of Behavior and Brain Sciences. He regularly serves as a consultant on topics in Artificial Intelligence and related areas.

• B.E. Electronics Engg., B.M.S.C.E., Bangalore University, Bangalore, Karnataka, India
• M.S. Electrical & Computer Engg., Drexel University, Philadelphia, Pennsylvania.
• 1988 Connectionist Models Summer School, Carnegie Mellon University, Pittsburgh.
• 1988 Summer Workshop on Parallel Computing, Argonne National Laboratory, Chicago.
• M.S. 1989, Computer Science, University of Wisconsin, Madison, Wisconsin
• 1989 Summer Institute in Cognitive Neuroscience, Dartmouth College.
• Ph.D. 1990, Computer Science and Cognitive Science
  (Artificial Intelligence), University of Wisconsin, Madison, Wisconsin

• Associate Professor, Department of Computer Science, Iowa State University.
• Director, Artificial Intelligence Research Laboratory, Department of Computer Science, Iowa State University.
• Co-Editor-in-Chief, Journal of Cognitive Systems Research, Published by Elsevier.
• Iowa State University Representative, Information Institute, Information Directorate, U.S. Air Force Research Laboratory, Rome, NY.
• Faculty member, Iowa Computational Biology Laboratory, Iowa State University.
• Faculty member, Interdepartmental Graduate Program in Neuroscience, Iowa State University.
• Coordinator, Complex Adaptive Systems Program, Iowa State University.

Research and Teaching Interests

Vasant Honavar's research and teaching interests span a number of areas including:

• Adaptive Systems
• Artificial Intelligence
• Artificial Neural Networks
• Autonomous Intelligent Robots
• Bioinformatics and Computational Biology
• Cognitive Science
• Complex Adaptive Systems
• Computational and Cognitive Neuroscience
• Data Mining and Knowledge Discovery
• Evolutionary Computation
• Intelligent Agents, Mobile Agents, and Multi-Agent Systems
• Intelligent Diagnosis Systems
• Intelligent Information Systems
• Intelligent Design and Manufacturing Systems
• Grammar Inference
• Knowledge-Based Systems
• Machine Learning and Discovery
• Machine Perception
• Medical Informatics
• Neural Architectures for Knowledge Representation and Inference
• Parallel and Distributed Computing
• Spatial and Temporal Knowledge Representation and Inference

Following is a brief overview of current research projects in Honavar's laboratory along with a few representative publications which provide more detailed information. A more complete list of publications can be found here. This research has been partially supported through grants from the National Science Foundation, the John Deere Foundation, and Iowa State University as well as research fellowships from IBM Corporation and the Iowa State University Graduate College.

Constructive Neural Network Learning Algorithms for Pattern Classification: Honavar's current research on neural network learning algorithms focuses on theory, design and experimental study of a family of efficient and provably convergent algorithms for incremental construction of neural networks for pattern classification and related machine learning applications. Constructive algorithms obviate the need for a-priori and often ad-hoc choices of network architectures. They can potentially yield near minimal networks whose size and complexity are commensurate with the complexity of the pattern recognition task (implicitly specified by the given dataset). In this context, inductive bias, incorporation of prior knowledge, cumulative multi-task learning are among the topics that are currently being explored. Related work explores automated feature subset selection and feature construction algorithms.

• Honavar, V., Parekh, R., and Yang, J. (1998). Structural Learning. Invited article. In: Encyclopedia of Electrical and Electronics Engineering, Webster, J. (Ed.), New York: Wiley. In press.
• Parekh, R. and Honavar, V. (1998). Constructive Theory Refinement in Knowledge Based Neural Networks. In: Proceedings of the International Joint Conference on Neural Networks. Anchorage, Alaska. 1998.
• Parekh, R., Yang, J., and Honavar, V. (1998). Constructive Neural Network Learning Algorithms for Multi-Category Pattern Classification. IEEE Transactions on Neural Networks. To appear. [parekh97a], [parekh97b], [yang96a], and [chen95].
• Yang, J. and Honavar, V. (1998). Feature Subset Selection Using a Genetic Algorithm. In: Feature Extraction, Construction, and Subset Selection: A Data Mining Perspective. Motoda, H. and Liu, H. (Ed.) New York: Kluwer. 1998. In press. A shorter version of this paper appears in IEEE Intelligent Systems (Special Issue on Feature Transformation and Subset Selection).
• Yang, J. and Honavar, V. (1998). DistAl: An Inter-Pattern Distance Based Constructive Neural Network Learning Algorithm.. Intelligent Data Analysis. In press. A preliminary version of this paper appears in [ijcnn98].

Intelligent Agents, Mobile Agents, and Multi-Agent Systems: Intelligent agents, mobile agents, and multi-agent systems offer a particularly attractive approach for the design and implementation of complex, flexible, and scalable information systems. Honavar's current research in this area focuses on the principles, design, and implementation of distributed knowledge networks (DKN) for information retrieval, information extraction, data-driven knowledge discovery, data and knowledge organization and assimilation, distributed problemsolving and decision support. Applications of DKN are bein explored in organizational decision support, bioinformatics, adaptive self-managing communication networks, intrusion detection, and distributed design and manufacturing.

• Honavar, V. (1998). Intelligent Agents. Invited chapter. In: Encyclopedia of Information Technology. Williams, J.G. and Sochats, K. (ed). New York: Marcel Dekker. To appear.
• Honavar, V., Miller, L. and Wong, J. (1998). Distributed Knowledge Networks. In: Proceedings of the IEEE Information Technology Conference. Syracuse, NY.
• Helmer, G., Wong, J., Honavar, V. and Miller, L. (1998). Intelligent Agents for Intrusion Detection. In: Proceedings of the IEEE Information Technology Conference. Syracuse, NY.
• Miller, L., Honavar, V. and Wong, J. (1998). Object-Oriented Data Warehouse for Information Fusion from Heterogeneous Data and Knowledge Sources. In: Proceedings of the IEEE Information Technology Conference. Syracuse, NY.
• Yang, J., Pai, P., Honavar, V., and Miller, L. (1998). Mobile Intelligent Agents for Document Classification and Retrieval: A Machine Learning Approach. In: Proceedings of the European Symposium on Cybernetics and Systems Research.
• Yang, J., Havaldar, R., Honavar, V., Miller, L. and Wong, J. (1998). Coordination and Control of Distributed Knowledge Networks Using the Contract Net Protocol. In: Proceedings of the IEEE Information Technology Conference. Syracuse, NY.
• Naganathan, V., Wong, J., Honavar, V., and Miller, L. (1998). Design and Implementation of a Mobile Agent Infrastructure. To appear.
• Honavar, V., Wong, J., Miller, L. (1997). Adaptive Information Retrieval Agents.To appear.
• Mikler, A., Honavar, V. and Wong, J. (1995). Heuristics for Intelligent Adaptive Routing in Large Communication Networks. Under review. A preliminary version appeared in [mikler96].

Data Mining and Knowledge Discovery: Honavar's current research on data mining and knowledge discovery focuses on the design and implementation of tools for large scale automated data extraction (using text processing, image processing, speech recognition, information retrieval tools), knowledge acquisition and discovery (using machine learning) from heterogeneous (e.g., dictionaries, books, web pages, images, relational and object-oriented databases, bibliographic databases, etc.), distributed data sources. As part of this project, a modular and extensible toolkit of machine learning algorithms (KADLab) is being implemented.

• Honavar, V. (1998). Inductive Learning: Principles and Applications. Invited chapter In: Cartwright, H. (Ed). Intelligent Data Analysis in Science, London: Oxford University Press.
• Parekh, R. and Honavar, V. (1998). Constructive Theory Refinement in Knowledge Based Neural Networks. In: Proceedings of the International Joint Conference on Neural Networks. Anchorage, Alaska. 1998.
• Parekh, R., Yang, J., and Honavar, V. (1998). Constructive Neural Network Learning Algorithms for Multi-Category Pattern Classification. IEEE Transactions on Neural Networks. To appear. [parekh97a], [parekh97b], [yang96a], and [chen95].
• Yang, J., Pai, P., Honavar, V., and Miller, L. (1998). Mobile Intelligent Agents for Document Classification and Retrieval: A Machine Learning Approach. In: Proceedings of the European Symposium on Cybernetics and Systems Research. In press.
• Yang, J. and Honavar, V. (1998). Feature Subset Selection Using a Genetic Algorithm. In: Feature Extraction, Construction, and Subset Selection: A Data Mining Perspective. Motoda, H. and Liu, H. (Ed.) New York: Kluwer. 1998. A shorter version of this paper appears in IEEE Intelligent Systems (Special Issue on Feature Transformation and Subset Selection).
• Yang, J. and Honavar, V. (1998). DistAl: An Inter-Pattern Distance Based Constructive Neural Network Learning Algorithm.. Intelligent Data Analysis. In press. A preliminary version of this paper appears in [ijcnn98].
• Balakrishnan, K. and Honavar, V. (1998). Intelligent Diagnosis Systems. Journal of Intelligent Systems. In press.
• Honavar, V. (1994). Toward Learning Systems That Use Multiple Strategies and Representations. In: Artificial Intelligence and Neural Networks: Steps Toward Principled Integration. pp. 615-644. Honavar, V. and Uhr, L. (Ed.) New York: Academic Press.

Bioinformatics and Computational Molecular Biology: Biological data (e.g., genetic and molecular data, ecological data, botanical data, zoological data) is being accumulated and stored in digital form at astronomical rates. There is a growing need for intelligent data analysis tools for automated knowledge acquisition and discovery from such data sources. Honavar's current research is aimed at the design, implementation, adaptation, and application of a broad range of machine learning tools for data analysis and knowledge discovery in biological and agricultural sciences. Much of this research is being conducted in collaboration with biologists who are experts in various domains of interest.

• Honavar, V. (1998). Inductive Learning: Principles and Applications. Invited chapter In: Cartwright, H. (Ed). Intelligent Data Analysis in Science, London: Oxford University Press.
• Honavar, V. (1998). Machine Learning: Principles and Applications. Invited Chapter In: Webster, J. (Ed.) Encyclopedia of Electrical and Electonics Engineering., New York: Wiley.
• Parekh, R. and Honavar, V. (1997). Constructive Theory Refinement: A New Algorithm and Experimental Results on Some Biological Datasets. To appear. Preliminary version of parts of this paper appear in: [ijcnn98].
• Balakrishnan, K. and Honavar, V. (1997). Intelligent Diagnosis Systems. Journal of Intelligent Systems. In press.
• Honavar, V. (1994). Toward Learning Systems That Use Multiple Strategies and Representations. In: Artificial Intelligence and Neural Networks: Steps Toward Principled Integration. pp. 615-644. Honavar, V. and Uhr, L. (Ed.) New York: Academic Press.

Evolutionary Robotics and Artificial Life: Evolutionary algorithms (genetic algorithms, evolution strategies, genetic programming, evolutionary programming) offer an attractive paradigm for automated synthesis of sensory, behavior, and control structures for robots and intelligent agents. Honavar's current research in this area is focused on automated synthesis of neural networks, finite automata, and computational architectures for reactive and deliberative behavior in intelligent autonomous agents and robots under a variety of cost, performance, and environmental constraints. Related research explores evolution of communication, cooperation, and language in communities of intelligent agents.

• Balakrishnan, K. & Honavar, V. (1999). Experiments in Evolutionary Robotics. In: Advances in Evolutionary Synthesis of Neural Systems. Patel, M. & Honavar, V. (Ed). Cambridge, MA: MIT Press. To appear. Preliminary versions of parts of this paper have appeared in: [bala97], [bala96a], [bala96b], [bala96c], and [bala95].
• Honavar, V. and Patel, M. (1999). Evolutionary Synthesis of Neural Systems. In: Advances In Evolutionary Synthesis of Neural Systems. Patel, M. and Honav ar, V. (ed). Cambridge, MA: MIT Press. In press.

Automata Induction, Grammar Inference, and Language Acquisition: Automata induction, the task of infering an unknown grammar (or equivalently, the corresponding recognition device) from examples finds applications in several areas including structural pattern recognition, language learning, information retrieval and computational biology. Honavar's research on grammar inference explores the design and analysis of algorithms for induction of regular grammars within different models of interaction between the learner and the environment. Of particular interest are models of language learning from simple examples, induction of large regular grammars, tree grammars and attributed grammars as well as acquisition of semantics along with syntax.

• Parekh, R.G. and Honavar, V. (1997) Learning DFA from Simple Examples. In: Proceedings of the Eighth International Workshop on Algorithmic Learning Theory, Sendai, Japan.
• Parekh, R. & Honavar, V. (1997). Automata Induction, Grammar Inference, and Language Acquisition. Invited chapter. In: Handbook of Natural Language Processing. Dale, Moisl & Somers (Ed). New York: Marcel Dekker. In press.

Spatial and Temporal Knowledge Representation and Inference: Honavar's research on knowledge representation focuses on techniques for representation of, and reasoning with, spatial and temporal knowledge under uncertainty, and their applications in robotics (e.g., acquisition and use of spatial maps for navigation), distributed multi-agent problem solving (e.g., utility-theoretic approaches to heuristic routing in large communication networks), and multi-agent systems.

• Balakrishnan, K., Bousquet, O. and Honavar, V. (1998). Spatial Learning and Localization in Animals: A Computational Model and Its Implications for Mobile Robots, Adaptive Behavior. In press.
• Kirillov, V. and Honavar, V. (1995). Simple Stochas tic Temporal Constraint Networks. Under review. Draft available as: ISU CS-TR 95-16.
• Mikler, A., Honavar, V. and Wong, J. (1995). Heuristics for Intelligent Adaptive Routing in Large Communication Networks. Under review. Preliminary version of a part of this paper appeared in [mikler96].

Massively Parallel Architectures for Knowledge Representation and Inference: Artificial neural networks, because of their massive parallelism and potential for fault tolerance provide an attractive paradigm for the implementation of high performance computer systems for knowledge representation and inference for real-time applications. Honavar's research on neural architectures for knowledge representation and reasoning focuses on fault-tolerant neural network architectures for associative memories, data storage and retrieval, syntax analysis, and deductive inference.

• Chen, C-H. & Honavar, V. (1998). A Neural Architecture for Syntax Analysis. (ISU CS-TR 95-18a). IEEE Transactions on Neural Networks. To appear.
• Chen, C-H. & Honavar, V. (1998). A Neural Architecture for Information Retrieval and Query Processing. Invited chapter. In: Handbook of Natural Language Processing. Dale, Moisl & Somers (Ed). New York: Marcel Dekker. To appear.
• Chen, C-H. and Honavar, V. (1995). A Neural Memory Architecture for Content as well as Address-Based Storage and Recall: Theory and Applications Connection Science. vol. 7. pp. 293-312.
• Honavar, V. (1994). Symbolic Artificial Intelligenc e and Numeric Artificial Neural Networks: Toward a Resolution of the Dichotomy. Invited chapter. In: Computational Architectures Integrating Symbolic and Neural Processes. pp. 351-388. Sun, R. and Bookman, L. (Ed.) New York: Kluwer.

Computational Models of Learning, Memory, and Behavior: Honavar's laboratory is involved in interdisciplinary research on learning and memory, with particular emphasis on design and theoretical and experimental analysis of and computational models of cognitive phenomena. This often leads to design and implementation of biologically inspired computational architectures for intelligence for applications in robotics and intelligent agents. Of particular interest are spatial learning and navigation in animals and computational investigation of the role of neuron-glia, glia-neuron, and glia-glia interactions in learning and memory.

• Balakrishnan, K., Bousquet, O. and Honavar, V. (1998). Spatial Learning and Localization in Animals: A Computational Model and Its Implications for Mobile Robots, Adaptive Behavior. In press.
• Honavar, V. and Uhr, L. (1990). Coordination and Control Structures and Processes: Possibilities for Connectionist Networks. Journal of Experimental and Theoretical Artificial Intelligence 2: 277-302.
• Honavar, V. and Uhr, L. (1989). Brain-Structured Connectionist Networks that Perceive and Learn. Connection Science 1: 139-160.

Applied Artificial Intelligence: Honavar's laboratory works on various topics in applied artificial intelligence including pattern recognition, modelling, prediction, optimization and control problems in bioinformatics, protein structure prediction, computational genomics, robotics, image analysis, power systems, manufacturing systems, engineering design, diagnosis, computer security, communication systems, finance, and medical informatics. This work employs a broad range of artificial intelligence tools including knowledge-based systems, artificial neural networks, statistical pattern recognition, evolutionary computing, machine learning, and intelligent agents. Some of this research is carried out in collaboration with industrial partners.

• Balakrishnan, K. and Honavar, V. (1998). Intelligent Diagnosis Systems. Journal of Intelligent Systems. In press.
• Helmer, G., Wong, J., Honavar, V. and Miller, L. (1998). Intelligent Agents for Intrusion Detection. In: Proceedings of the IEEE Information Technology Conference. Syracuse, NY.
• Honavar, V., Miller, L. and Wong, J. (1998). Distributed Knowledge Networks. In: Proceedings of the IEEE Information Technology Conference. Syracuse, NY.
• Mikler, A., Wong, J. and Honavar, V. (1997). Quo Vadis - A Framework for Intelligent Routing in Large Communication Networks. The Journal of Systems and Software. 37 61-73.
• Zhou, G., McCalley, J. D. and Honavar, V. (1997). Power System Security Margin Prediction Using R adial Basis Function Networks. In: Proceedings of the 29th Annual North A merican Power Symposium. Laramie, Wyoming. October 13-14, 1997.

Other Topics of Current Interest: Other topics of interest include: Computational Models of Discovery; Computational Models of Creativity; Computational Modeling and Simulation of Complex Systems (evolution, social systems, immune systems, communication networks, etc.); Hybrid Intelligent Systems; Philosophy of Mind; Intelligent Design and Manufacturing Systems; Applications of information theory and complexity theory (in particular, Kolmogorov complexity, minimum description length, and related topics) in computational learning theory and biology.

Honavar's research is partially supported by grants from the National Science Foundation and the John Deere Foundation.

A more complete list of publications can be found here

• Honavar, V. and Slutzki, G. (1998) (Ed.). Proceedings of the Fourth International Colloquium on Grammatical Inference. (LNCS Vol. 1433). Berlin: Springer-Verlag.
• Patel. M. and Honavar, V. (1998) (Ed). Advances in Evolutionary Synthesis of Neural Systems. Boston, MA: MIT Press. To appear.
• Honavar, V. and Uhr, L. (1994) (Ed). Artificial Intelligence and Neural Networks: Steps Toward Principled Integration. New York, NY: Academic Press.

• Ph.D. Graduates
  • Armin Mikler, 1995. (Co-advised with Johnny Wong). Thesis: Quo-Vadis - A Framework for Intelligent Routing in Large Communication Networks. Employment: Assistant Professor, Department of Computer Science, University of North Texas, Denton, TX.
  • Chun-Hsien Chen, 1997. Thesis: Neural Architectures for Associative Memory, Syntax Analysis, Knowledge Representation, and Inference. Employment: Research Scientist, Computer and Communications Research Laboratories, Industrial Technology Research Institute, Taiwan.
  • Rajesh Parekh, 1998. Constructive Learning Algorithms: Inducing Grammars and Neural Networks. Employment: Research Scientist, Allstate Research and Planning Center, Menlo Park, CA.
  • Karthik Balakrishnan., 1998. Biologically Inspired Information Processing Structures for Autonomous Agents and Robots. Employment: Research Scientist, Allstate Research and Planning Center, Menlo Park, CA.
• M.S. Graduates
  • Di Wang, 1998. Initial Employment: Consulting, Toronto.
  • Shane Konsella, 1997. Initial Employment: Hewlett-Packard.
  • Karthik Balakrishnan, 1993. Ph.D. Student, Iowa State University.
  • Rajesh Parekh, 1993. Ph.D. Student, Iowa State University.
  • Jayathi Janakiraman, 1993. Initial Employment: Motorola.
  • Priyamvadha Thambu, 1993. Initial Employment: Inference Corporation.
  • Richard Spartz, 1992. Initial Employment: IBM (Rochester, MN).
• Current Students
  • Jihoon Yang. Adaptive Information Retrieval and Knowledge Discovery Agents. Ph.D. Candidate. Expected Graduation: Fall 1998.
  • Rushi Bhatt. Interests: Artificial Intelligence, Computational Neuroscience and Cognitive Modeling.
  • Doina Caragea. Interests: Distributed Knowledge Networks, Multiagent Systems, Machine Learning, Neural Networks, Data Mining, Computational Biology and Bioinformatics.
  • Fajun Chen. Interests: Distributed Knowledge Networks, Multiagent Systems, Machine Learning, Data Mining, Computational Biology and Bioinformatics.
  • Asok Tiyyagura. Interests: Artificial Intelligence Applications in Power Systems, Neural Networks, Evolutionary Computing, Machine Learning, Data Mining, Distributed Knowledge Networks.
  • Adrian Silvescu. Interests: Distributed Knowledge Networks, Multi-Agent Systems, Machine Learning, Computational Biology and Bioinformatics.
  • Tarkeshwari Sharma. Interests: Data Mining and Knowledge Discovery, Data Warehouses.

Catalog descriptions and information about scheduled offerings for the courses can be found here.

• Principles of Artificial Intelligence ComS 572 (472 DL).
• Elements of Neural Computation ComS 474.
• Computational Models of Learning ComS 672.
• Advanced Topics in Artificial Intelligence and Cognitive Modelling ComS 673.
• Artificial Intelligence Research Seminar ComS 610VH.
• Seminar on Intelligent Systems in Molecular Biology ComS 610VH.
• Intelligent Agents and Multi-Agent Systems Seminar ComS VH.
• Directed Independent Study and Research (ComS 290, 290H, 490, 490H, 590, 599, 699).

In Fall 1996, I ran the Graduate Orientation Seminar (ComS 591).

In Fall 1997, I co-taught (with over a half-dozen other faculty), a graduate seminar in Computational Molecular Biology.

• Professional Organizations
  • Member, Institution of Electrical and Electronic Engineers (IEEE)
  • Member, Association for Computing Machinery (ACM)
  • Member, American Association for Artificial Intelligence (AAAI)
  • Elected Member, New York Academy of Sciences (NYAS)
  • Member, American Association for the Advancement of Science (AAAS)
  • Member, International Neural Networks Society (INNS)
  • Associate, Behavioural and Brain Sciences (BBS)
  • Elected Member, Sigma Xi
  • Member, Society for Neuroscience
  • Member, Cognitive Science Society
  • Member, ACM Special Interest Group In Artificial Intelligence (SIGART)
  • Member, Neural Networks Council (NNC)

• Recent Conferences
  • Artificial Life, Adaptive Behavior, and Agents Committee Chair Genetic and Evolutionary Computing Conference, Orlando, Florida, July 1999.
  • Chair, Fourth International Colloquium on Grammatical Inference (ICGI 98), Ames, Iowa. July 1998.
  • Program Committee Member, Genetic Programming Conference, 1998 (GP-98), Madison, Wisconsin, July 1998.
  • Program Committee Member, Ninth Midwest Artificial Intelligence and Cognitive Science Conference, Dayton, Ohio, March 1998.
  • Member of International Advisory Committee, International Conference on Evolutioanary Computation in Engineering (ICECE 99), Madras, India, January 1999.
  • Program Committee Member, Fourteenth International Conference on Machine Learning, Nashville, TN. July 1997.
  • Organizer and Co-Chair, Workshop on Automata Induction, Grammatical Inference, and Language Acquisition International Conference on Machine Learning, Nashville, TN. July 1997.
  • Program Committee Member, Genetic Programming 1997 Stanford University, CA. July 1997.
  • Session Chair, International Conference on Neural Networks, Houston, TX. June 1997.
  • Program Committee Member, Eighth Midwest Artificial Intelligence and Cognitive Science Conference (MAICS97), Dayton, Ohio. May 1997.
  • Advisory Committee Member, Fifth International Conference on AI Applications, Cairo, Egypt. July 1997.
  • Program Committee Member and Session Chair, World Congress on Neural Networks (WCNN-96), San Diego, CA. Session on Evolutionary / Genetic / Annealing Algorithms.
  • Program Committee Member, Genetic Programming Conference (GP-96), Stanford, CA.
  • Program Committee Member, Midwest Artificial Intelligence and Cognitive Science Meeting (MAICS-96), Bloomington, Indiana.
  • Program Committee Member and Session Chair, World Congress on Neural Networks, Washington, DC., July 1995.
  • Program Committee Member, Midwest Artificial Intelligence and Cognitive Science Meeting, Carbondale, IL. April 1995.

• Referee
  • IEEE Transactions on Neural Networks
  • IEEE Transactions on Knowledge and Data Engineering
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • IEEE Transactions on Evolutionary Computation
  • IEEE Expert
  • IEEE Computer
  • Applied Intelligence
  • Neural Networks
  • Neural Computation
  • Information Sciences
  • Connection Science
  • Image and Vision Computing
  • Microcomputer Applications
  • Numerous National and International Conferences

• Panels and Workshops
  • Review Panel, CISE Research Instrumentation Program, National Science Foundation, 1994.
  • NSF Workshop on Decision-Based Design, Sacramento, CA. September 1997.
  • Panel on Hybrid Architectures for Intelligent Systems, World Congress on Expert Systems, Lisbon, Portugal, 1994.
  • Panel on Learning in Knowledge-based Systems, World Congress on Expert Systems, Lisbon, Portugal, 1994.

• Department, College, and University Committees
  • Cognitive Science Steering Committee, 1997.
  • Neuroscience Program Supervisory Committee, 1996-
  • Graduate Committee, Computer Science Dept. 1996-;
  • Graduate Admissions Committee, Computer Science Dept. 1990-1996.
  • Liberal Arts and Sciences Honors Program Committee, 1992-1994.