Lokendra Shastri

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.

Research Projects:

SHRUTI: From Simple Associations to Systematic Reasoning

We are trying to understand how networks of slow neuron-like elements can encode a large body of knowledge and perform a wide range of explanatory and predictive inferences within hundreds of milliseconds. This model also explores the possible role of temporal synchrony in the expression and processing of relational knowledge and dynamic bindings.

High-performance knowledge based reasoning systems.

SMRITI: Episodic Memory Formation via Cortico-Hippocampal Interactions.

Spatio-temporal Connectionist Networks for Speech and Visual Pattern Recognition..

Learning abstract rules (re: Infant learning algebraic rules).

From Sound to Meaning.

Research Agents and Inferential Retrieval.

Other Information:

Selected Bibliography ... Selected Professional Activities ... Teaching ... Brief CV

Lokendra Shastri International Computer Science Institute Berkeley, CA 94704 Phone: (510) 666-2910 FAX: (510) 666-2956

  shastri     . . . this should
  @icsi.      . . . keep out
  berkeley.   . . . some of the
  edu         . . . spam