Encoding Strategy for Maximum Noise Tolerance Bidirectional Associative Memory

Abstract

In this paper, the Basic Bidirectional Associative Memory (BAM) is extended by choosing weights in the correlation matrix, for a given set of training pairs, which result in a maximum noise tolerance set for BAM. This optimized BAM will recall the correct training pair if an input pair is within the maximum noise tolerance set. We define a hyper-radius, and we prove that for a given set of training pairs, the maximum noise tolerance set is the largest, in the sense that at least one pair outside the maximum noise tolerance set, and within a Hamming distance one larger than the hyper-radius associated with the maximum noise tolerance set, will not converge to the correct training pair. A standard Genetic Algorithm (GA) is used to calculate the weights to maximize the objective function which generates a maximum tolerance set for BAM. Computer simulations are presented to illustrate the error correction and fault tolerance properties of the optimized BAM.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2003
Accession Number
ADA416239

Entities

People

  • Dan Shen
  • Jose B. Cruz Jr.

Organizations

  • Ohio State University

Tags

DTIC Thesaurus Topics

  • Air Force
  • Air Force Facilities
  • Air Force Research Laboratories
  • Aircrafts
  • Algorithms
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Coding
  • Content Addressable Memory
  • Decoding
  • Energy
  • Genetic Algorithms
  • Information Systems
  • Neural Networks
  • Recurrent Neural Networks
  • Standards
  • Training

Readers

  • Applied Combinatorial Optimization and Logic Circuit Design.
  • Neural Network Machine Learning.
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Biotechnology