LOKENDRA SHASTRI

International Computer Science Institute
1947 Center St., Suite 600
Berkeley, CA 94704.

(510)-666-2910
shastri at icsi dot berkeley dot edu
http://www.icsi.berkeley.edu/$\sim$shastri

Education

1985

Ph.D., Computer Science, University of Rochester.

1980

M.S., Computer Science, Indian Institute of Technology, Madras, India.

1977

B.E. (honors), Electronics Engineering, with Distinction, Birla Institute of Technology and Science, Pilani, India.

Academic and Research Positions

Since 1993, Dr. Shastri has been a Principal Investigator and Member of the AI Group at the International Computer Science Institute, Berkeley, CA. Before moving to ICSI, Berkeley, he was on the faculty of the Department of Computer and Information Science, University of Pennsylvania.

Research interests

Artificial Intelligence, Cognitive Science, and Computational and Cognitive Neuroscience: scalable, neurally motivated models of knowledge representation and reasoning, learning, memory, and decision making; reasoning with very large knowledge bases; episodic memory and cortico-hippocampal interactions; temporal synchrony in neural information processing; spatio-temporal pattern recognition; semantic networks.

Training and Human Resources

Dr. Shastri has supervised several doctoral dissertations in the areas of spatiotemporal connectionist models of speech and handwriting recognition, knowledge representation, inference, and learning. He has also supervised many Post-doctoral fellows in the areas of dynamic feature binding, incremental learning, and hierarchical self-organizing maps for recognizing complex events, and a neurally plausible architecture for planning.

Professional Activities

Dr. Shastri has authored one book and over sixty refereed publications in the areas of connectionist models of knowledge representation and reasoning, spatio-temporal neural networks for speech and handwriting recognition, and episodic memory formation. He is on the advisory board of ``Neural Computing Surveys'' and the editorial board of ``Connection Science'', and he has served on numerous program committees and review panels. He has consulted for the Policy Research and Analysis Division of the National Science Foundation, the United Nations Development Programme, and SRI International.

Ten representative publications

1. Shastri, L. Episodic memory and cortico-hippocampal interactions, Trends in Cognitive Sciences, 6:162-168. 2002. pdf
   

2. Shastri, L. ``A Computationally Efficient Abstraction of Long-term Potentiation,'' Neurocomputing, 44-46: 33-41. 2002. pdf

3. Shastri, L. ``A computational model of episodic memory formation in the hippocampal system,'' Neurocomputing, 38-40: 889-897, 2001. (Also in Bower, J. (ed.) Computational Neuroscience, Trends in Research 2001, Elsevier, Amsterdam). pdf

4. Shastri, L. & Wendelken, C. (2000) ``Seeking coherent explanations -- a fusion of structured connectionism, temporal synchrony, and evidential reasoning,'' Proceedings of the Twenty Second Annual Conference of the Cognitive Science Society, pp. 453-458 Philadelphia, PA. August 2000.

5. Shastri, L. (1999) Advances in SHRUTI - a neurally motivated model of relational knowledge representation and rapid inference using temporal synchrony. Applied Intelligence, 11, 79-108.

6. Mani, D.R. & Shastri, L. (1999) ``Parallel Inference with Very Large Knowledge Bases,'' In High Performance Cluster Computing 2, (Ed.) R. Buyya, Prentice Hall.

7. Shastri, L. (1996) Temporal Synchrony, Dynamic Bindings, and SHRUTI: a representational but non-classical model of reflexive reasoning. Behavioral and Brain Sciences Vol. 19, No. 2, 326-337, 1996.

8. Shastri, L. & Ajjanagadde, V. (1993) From simple associations to systematic reasoning: a connectionist representation of rules, variables, and dynamic bindings using temporal synchrony. Behavioral and Brain Sciences Vol. 16, No. 3, 417-494, 1993.

9. Ajjanagadde, V. and Shastri, L. (1991) ``Rules and variables in neural nets'', Neural Computation. 3, 121-134, 1991.

10. Shastri, L. (1988) ``A connectionist approach to knowledge representation and limited inference'', Cognitive Science, Vol. 12, No. 3, 331-392, 1988.