Title
From Bidirectional Associative Memory to a noise-tolerant, robust Protein Processor Associative Memory
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.
Year
DOI
Venue
2011
10.1016/j.artint.2010.10.008
Artif. Intell.
Keywords
Field
DocType
novel architecture,recent associative memory architecture,associations incrementally,e-puck mobile robot,typical weighted-sum arithmetic operation,bidirectional associative memory,protein processor associative memory,actual implementation,original training algorithm,arithmetic operation,robust protein processor associative,associative memory,mobile robot
Content-addressable memory,Computer science,Bidirectional associative memory,Artificial intelligence,Memory map,Artificial neural network,Recall,Machine learning,Memory architecture,Mobile robot,Scalability
Journal
Volume
Issue
ISSN
175
2
0004-3702
Citations 
PageRank 
References 
8
0.53
16
Authors
5
Name
Order
Citations
PageRank
Omer Qadir1111.60
Jerry Liu2828.65
Gianluca Tempesti345757.09
Jon Timmis41237120.32
Andy Tyrrell515813.74