Neural associative memory for brain modeling and information retrieval

Authors:
Andreas Knoblauch
Affiliations:
Department of Neural Information Processing, University of Ulm, Oberer Eselsberg, D-89069 Ulm, Germany and MRC Cognition and Brain Sciences Unit, Speech and Language Group, 15 Chaucer Road, Cambri ...
Venue:
Information Processing Letters - Special issue on applications of spiking neural networks
Year:
2005

Citing 9
Cited 4

Bidirectional associative memories

IEEE Transactions on Systems, Man and Cybernetics
Methods in Neuronal Modeling: From synapses to networks

Methods in Neuronal Modeling: From synapses to networks
Iterative retrieval of sparsely coded associative memory patterns

Neural Networks
Improved bidirectional retrieval of sparse patterns stored by Hebbian learning

Neural Networks
Perceptrons: An Introduction to Computational Geometry

Perceptrons: An Introduction to Computational Geometry
Multi-index hashing for information retrieval

SFCS '94 Proceedings of the 35th Annual Symposium on Foundations of Computer Science
Optimal matrix compression yields storage capacity 1 for binary Willshaw associative memory

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Run-length encodings (Corresp.)

IEEE Transactions on Information Theory
A VLSI recurrent network of integrate-and-fire neurons connected by plastic synapses with long-term memory

IEEE Transactions on Neural Networks

Memory capacities for synaptic and structural plasticity

Neural Computation
Integrated feature and parameter optimization for an evolving spiking neural network

ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Neural associative memory with optimal bayesian learning

Neural Computation
Integer sparse distributed memory: Analysis and results

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work concisely reviews and unifies the analysis of different variants of neural associative networks consisting of binary neurons and synapses (Willshaw model). We compute storage capacity, fault tolerance, and retrieval efficiency and point out problems of the classical Willshaw model such as limited fault tolerance and restriction to logarithmically sparse random patterns. Then we suggest possible solutions employing spiking neurons, compression of the memory structures, and additional cell layers. Finally, we discuss from a technical perspective whether distributed neural associative memories have any practical advantage over localized storage, e.g., in compressed look-up tables.