Rapid learning and robust recall of long sequences in modular associator networks

Authors:
Michael Lawrence;Thomas Trappenberg;Alan Fine
Affiliations:
Dalhousie University, Halifax, Canada;Dalhousie University, Halifax, Canada;Dalhousie University, Halifax, Canada
Venue:
Neurocomputing
Year:
2006

Citing 6
Cited 3

Self-organizing continuous attractor networks and motor function

Neural Networks
Temporal Sequence Learning, Prediction, and Control: A Review of Different Models and Their Relation to Biological Mechanisms

Neural Computation
Cognitive Map Formation Through Sequence Encoding by Theta Phase Precession

Neural Computation
2005 Special issue: Interpreting hippocampal function as recoding and forecasting

Neural Networks - Special issue: Computational theories of the functions of the hippocampus
Synfire chains with conductance-based neurons: internal timing and coordination with timed input

Neurocomputing
Heteroassociations of spatio-temporal sequences with the bidirectional associative memory

IEEE Transactions on Neural Networks

Improvement of learning algorithms for RBF neural networks in a helicopter sound identification system

Neurocomputing
Storage capacity comparison of neural network models for memory recall

Crossroads
Robust sequence memory in sparsely-connected networks with controllable steady-state period

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

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.