STUDY OF NEUROTRON NETWORKS IN LEARNING AUTOMATA.
Abstract
Extensive data and mathematical theory are presented on the computer simulation or Probability State Variable (PSV) devices, e.g., the Neurotron, Random State Variable (RSV) Strategy devices, and networks of these elements as a function of the network connectivity, and score and value functions in four problem classes: re-entry trajectory prediction, pattern recognition, inferential measurement techniques, and self-organizing controllers. The simulation models are presented in detail. Hardware implementation is discussed, using statistical source design as a vehicle for insight into cost analysis of the Demonstrator Neurotron and the feasibility of construction of the networks studied. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 06, 1965
- Accession Number
- AD0455688
Entities
People
- R. E. J. Moddes