Regarding the temporal requirements of a hierarchical Willshaw network

Authors:
João Sacramento;Francisco Burnay;Andreas Wichert
Affiliations:
INESC-ID Lisboa and Instituto Superior Técnico, Technical University of Lisbon, Av. Prof. Dr. Aníbal Cavaco Silva, 2744-016 Porto Salvo, Portugal;Instituto de Plasmas e Fusão Nuclear, Instituto Superior Técnico, Technical University of Lisbon, Av. Rovisco Pais, 1049-001 Lisboa, Portugal;INESC-ID Lisboa and Instituto Superior Técnico, Technical University of Lisbon, Av. Prof. Dr. Aníbal Cavaco Silva, 2744-016 Porto Salvo, Portugal
Venue:
Neural Networks
Year:
2012

Citing 15
Cited 0

Information storage and effective data retrieval in sparse matrices

Neural Networks
Regular Article: A Lower Bound on the Number of Solutions to the Probed Partial Digest Problem

Advances in Applied Mathematics
What is the goal of sensory coding?

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

Neural Networks
On the number of ordered factorizations of natural numbers

Discrete Mathematics
A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces

VLDB '98 Proceedings of the 24rd International Conference on Very Large Data Bases
Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions

Communications of the ACM - 50th anniversary issue: 1958 - 2008
On the information storage capacity of local learning rules

Neural Computation
Optimal plasticity from matrix memories: What goes up must come down

Neural Computation
Energy efficient neural codes

Neural Computation
Optimal learning rules for familiarity detection

Biological Cybernetics - Volume 100: Half a Century of Biological Cybernetics
Memory capacities for synaptic and structural plasticity

Neural Computation
Neural networks letter: Tree-like hierarchical associative memory structures

Neural Networks
Neural associative memory with optimal bayesian learning

Neural Computation
Nearest neighbor pattern classification

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.01

Visualization

Abstract

In a recent communication, Sacramento and Wichert (2011) proposed a hierarchical retrieval prescription for Willshaw-type associative networks. Through simulation it was shown that one could make use of low resolution descriptor patterns to decrease the total time requirements of recalling a learnt association. However, such a method introduced a dependence on a set of new parameters which define the structure of the hierarchy. In this work we compute the expected retrieval time for the random neural activity regime which maximises the capacity of the Willshaw model and we study the task of finding the optimal hierarchy parametrisation with respect to the derived temporal expectation. Still in regard to this performance measure, we investigate some asymptotic properties of the algorithm.