A novel Episodic Associative Memory model for enhanced classification accuracy

Authors:
L. K. Wickramasinghe;L. D. Alahakoon;K. Smith-Miles
Affiliations:
Clayton School of Information Technology, P.O. Box 63B, Monash University, Vic. 3800, Australia;Clayton School of Information Technology, P.O. Box 63B, Monash University, Vic. 3800, Australia;School of Engineering and Information Technology, Deakin University, Burwood, Vic. 3125, Australia
Venue:
Pattern Recognition Letters
Year:
2007

Citing 6
Cited 4

On the complexity of loading shallow neural networks

Journal of Complexity - Special Issue on Neural Computation
Connectionist learning procedures

Artificial Intelligence
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Convergence-zone episodic memory: analysis and simulations

Neural Networks
Data mining: practical machine learning tools and techniques with Java implementations

Data mining: practical machine learning tools and techniques with Java implementations
Correlation Matrix Memories

IEEE Transactions on Computers

A Bidirectional Hetero-Associative Memory for True-Color Patterns

Neural Processing Letters
A New Associative Model with Dynamical Synapses

Neural Processing Letters
Temporal association based on dynamic depression synapses and chaotic neurons

Neurocomputing
Future prediction with hierarchical episodic memories under deterministic and stochastic environments

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part I

Quantified Score

Hi-index	0.10

Visualization

Abstract

A novel approach to Episodic Associative Memory (EAM), known as Episodic Associative Memory with a Neighborhood Effect (EAMwNE) is presented in this paper. It overcomes the representation limitations of existing episodic memory models and increases the potential for their use in practical application.