Spatio-Temporal Neural Networks for Vision, Reasoning and Rapid Decision Making

Abstract

A spatio-temporal system for recognizing handprint digit strings was designed and trained to recognize handprinted ZIP codes. The results of our work on a biologically motivated model of reflexive reasoning were used to implement a pilot system for performing rapid reasoning using very large knowledge bases. The pilot system which runs on a 32 node CM-5, can encode over 300,000 items and respond in less than 500 msec. to queries requiring reasoning upto a depth of eight

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 31, 1994
Accession Number
ADA283251

Entities

People

  • Lokendra Shastri

Organizations

  • International Computer Science Institute

Tags

Communities of Interest

  • Energy and Power Technologies
  • Engineered Resilient Systems
  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Automata Theory
  • Birds
  • Brain
  • Cognitive Science
  • Computational Science
  • Computer Languages
  • Computer Programming
  • Computer Vision
  • Computers
  • Information Processing
  • Information Science
  • Information Systems
  • Psychology
  • Reasoning
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience
  • Computer Programming and Software Development.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks