Delay for the capacity-simplicity dilemma in associative memory attractor networks

Authors:
Shaofen Zou;Yuming Chen;Jianfu Ma;Jianhong Wu
Affiliations:
College of Mathematics and Econometrics, Hunan University, Changsha, Hunan 410082, China;Department of Mathematics, Wilfrid Laurier University, Waterloo, Ontario N2L 3C5, Canada;Department of Biochemistry and Molecular Biology, The University of Texas Health Science Center at Houston Medical School, Houston, TX 77225, USA;Department of Mathematics and Statistics, York University, Toronto, Ontario M3J 1P3, Canada
Venue:
Neural Networks
Year:
2012

Citing 19
Cited 0

A massively parallel architecture for a self-organizing neural pattern recognition machine

Computer Vision, Graphics, and Image Processing
The capacity of the Hopfield associative memory

IEEE Transactions on Information Theory
ARTMAP: Supervised real-time learning and classification of nonstationary data by a self-organizing neural network

Neural Networks
Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
Original Contribution: Associative memory with nonmonotone dynamics

Neural Networks
Capacity of associative memory using a nonmonotonic neuron model

Neural Networks
Spike frequency adaptation affects the synchronization properties of networks of cortical oscillators

Neural Computation
ARTMAP-IC and medical diagnosis: instance counting and inconsistent cases

Neural Networks
The Handbook of Brain Theory and Neural Networks

The Handbook of Brain Theory and Neural Networks
Projective ART for clustering data sets in high dimensional spaces

Neural Networks
Proper orthogonal decomposition based optimal neurocontrol synthesis of a chemical reactor process using approximate dynamic programming

Neural Networks - 2003 Special issue: Advances in neural networks research — IJCNN'03
Multistability in Spiking Neuron Models of Delayed Recurrent Inhibitory Loops

Neural Computation
2007 Special Issue: Consciousness CLEARS the mind

Neural Networks
Correlation Matrix Memories

IEEE Transactions on Computers
Large memory capacity in chaotic artificial neural networks: a view of the anti-integrable limit

IEEE Transactions on Neural Networks
Projective clustering using neural networks with adaptive delay and signal transmission loss

Neural Computation
Auto-associative memory with two-stage dynamics of nonmonotonic neurons

IEEE Transactions on Neural Networks
Dynamics of projective adaptive resonance theory model: the foundation of PART algorithm

IEEE Transactions on Neural Networks
Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We consider the issue of how a simple network with delayed feedback can exhibit complex but desired dynamical behaviors for memory storage and retrieval. We discuss the simplicity-capacity dilemma arising from the requirement of both large capacity and easy implementation in additive networks. We then propose a novel approach based on signal processing delay and show that the interaction of delay, feedback and refractoriness in a simple inhibitory network of three neurons can generate mathematically trackable coexisting periodic patterns. Therefore, a simple and small network with delayed feedback can process a large amount of information, and time lag in our biological or artificial neural nets is useful for information processing. How the connection topology of a large network enhances the network's capacity for memory storage and retrieval remains to be an interesting task.