From Bidirectional Associative Memory to a noise-tolerant, robust Protein Processor Associative Memory

Omer Qadir, Jerry Liu, Gianluca Tempesti, Jon Timmis, Andy Tyrrell

Research output: Contribution to journalArticlepeer-review

Abstract

Protein Processor Associative Memory (PPAM) is a novel architecture for learning associations incrementally and online and performing fast, reliable, scalable hetero-associative recall. This paper presents a comparison of the PPAM with the Bidirectional Associative Memory (BAM), both with Kosko's original training algorithm and also with the more popular Pseudo-Relaxation Learning Algorithm for BAM (PRLAB). It also compares the PPAM with a more recent associative memory architecture called SOIAM. Results of training for object-avoidance are presented from simulations using player/stage and are verified by actual implementations on the E-Puck mobile robot. Finally, we show how the PPAM is capable of achieving an increase in performance without using the typical weighted-sum arithmetic operations or indeed any arithmetic operations. (C) 2010 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)673-693
Number of pages21
JournalArtificial Intelligence
Volume175
Issue number2
DOIs
Publication statusPublished - Feb 2011

Keywords

  • Self-organising
  • Self-regulating
  • Associative Memory
  • Protein processing
  • Hetero-associative
  • BAM
  • PRLAB
  • SOIAM
  • SABRE
  • Mobile robotics
  • NEURAL-NETWORKS
  • PERFORMANCE
  • CIRCUITS
  • STRATEGY

Cite this