Abstract | ||
---|---|---|
Most heteroassociative memories models intend to achieve the recall of the entire trained pattern. The Alpha-Beta associative memories only ensure the correct recall of the trained patterns in autoassociative memories, but not for the heteroassociative memories. In this work we present a new algorithm based on the Alpha-Beta Heteroassociative memories that allows, besides correct recall of some altered patterns, perfect recall of all the trained patterns, without ambiguity. The theoretical support and some experimental results are presented. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-76631-5_19 | MICAI |
Keywords | Field | DocType |
alpha-beta heteroassociative memory,perfect recall,heteroassociative memories model,complete recall,alpha-beta associative memory,correct recall,trained pattern,altered pattern,heteroassociative memory,entire trained pattern,autoassociative memory,memory model,associative memory | Autoassociative memory,Associative property,Pattern recognition,Computer science,Artificial intelligence,Recall,Ambiguity,Machine learning | Conference |
Volume | ISSN | ISBN |
4827 | 0302-9743 | 3-540-76630-8 |
Citations | PageRank | References |
1 | 0.35 | 2 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Israel Román-Godínez | 1 | 4 | 1.12 |
Cornelio Yáñez-Márquez | 2 | 153 | 26.34 |