Neural networks letter: Tree-like hierarchical associative memory structures

Authors:
João Sacramento;Andreas Wichert
Affiliations:
-;-
Venue:
Neural Networks
Year:
2011

Citing 10
Cited 1

Information storage and effective data retrieval in sparse matrices

Neural Networks
Hierarchical concept formation in associative memory composed of neuro-window elements

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

Neural Networks
A cascade associative memory model with a hierarchical memory structure

Neural Networks
Subspace Tree

CBMI '09 Proceedings of the 2009 Seventh International Workshop on Content-Based Multimedia Indexing
Memory capacities for synaptic and structural plasticity

Neural Computation
Cell assemblies for diagnostic problem-solving

Neurocomputing
Storing and restoring visual input with collaborative rank coding and associative memory

Neurocomputing
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
Hierarchical associative memories: the neural network for prediction in spatial maps

ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing

Regarding the temporal requirements of a hierarchical Willshaw network

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this letter we explore an alternative structural representation for Steinbuch-type binary associative memories. These networks offer very generous storage capacities (both asymptotic and finite) at the expense of sparse coding. However, the original retrieval prescription performs a complete search on a fully-connected network, whereas only a small fraction of units will eventually contain desired results due to the sparse coding requirement. Instead of modelling the network as a single layer of neurons we suggest a hierarchical organization where the information content of each memory is a successive approximation of one another. With such a structure it is possible to enhance retrieval performance using a progressively deepening procedure. To backup our intuition we provide collected experimental evidence alongside comments on eventual biological plausibility.