Abstract | ||
---|---|---|
An extension to a recently introduced architecture of clique-based neural networks is presented. This extension makes it possible to store sequences with high efficiency. To obtain this property, network connections are provided with orientation and with flexible redundancy carried by both spatial and temporal redundancies, a mechanism of anticipation being introduced in the model. In addition to the sequence storage with high efficiency, this new scheme also offers biological plausibility. In order to achieve accurate sequence retrieval, a double-layered structure combining heteroassociation and autoassociation is also proposed. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/TNNLS.2015.2431319 | IEEE transactions on neural networks and learning systems |
Keywords | Field | DocType |
associative memory,directed graph,information theory,redundancy,sequential memory,sparse coding. | Content-addressable memory,Computer science,Theoretical computer science,Redundancy (engineering),Artificial intelligence,Cluster analysis,Artificial neural network,Information theory,Clique,Pattern recognition,Neural coding,Decoding methods,Machine learning | Journal |
Volume | Issue | ISSN |
PP | 99 | 2162-237X |
Citations | PageRank | References |
4 | 0.46 | 15 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaoran Jiang | 1 | 39 | 5.52 |
Vincent Gripon | 2 | 16 | 1.71 |
Claude Berrou | 3 | 4 | 0.46 |
Michael G. Rabbat | 4 | 5 | 0.84 |