Abstract | ||
---|---|---|
Biologically inspired neural networks which perform temporal sequence learning and generation are frequently based on hetero-associative memories. Recent work by Jensen and Lisman has suggested that a model which connects an auto-associator module to a hetero-associator module can perform this function. We modify this architecture in a simplified model which in contrast uses a pair of connected auto-associative networks with hetero-associatively trained synapses in one of the paths between them. We simulate both models, finding that accurate and robust recall of learned sequences can easily be performed with the modified model introduced here, strongly outperforming the previous architecture. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1016/j.neucom.2005.12.003 | Neurocomputing |
Keywords | Field | DocType |
rapid learning,neural network,hetero-associator module,connected auto-associative network,long sequence,modified model,sequence memory,robust recall,hetero-associatively trained synapsis,hetero-associations,recent work,hetero-associative memory,auto-associator module,modular associator network,previous architecture,sequence learning,associative memory | Architecture,Computer science,Artificial intelligence,Modular design,Artificial neural network,Recall,Sequence learning,Machine learning,Associator | Journal |
Volume | Issue | ISSN |
69 | 7-9 | Neurocomputing |
Citations | PageRank | References |
9 | 0.85 | 6 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Lawrence | 1 | 43 | 2.11 |
Thomas Trappenberg | 2 | 22 | 2.85 |
A Fine | 3 | 10 | 2.04 |