Improving VG-RAM neural networks performance using knowledge correlation

Authors:
Raphael V. Carneiro;Stiven S. Dias;Dijalma Fardin;Hallysson Oliveira;Artur S. d'Avila Garcez;Alberto F. De Souza
Affiliations:
Programa de Pós-Graduação em Informática, Universidade Federal do Espírito Santo, Vitória, ES, Brazil;Programa de Pós-Graduação em Informática, Universidade Federal do Espírito Santo, Vitória, ES, Brazil;Programa de Pós-Graduação em Informática, Universidade Federal do Espírito Santo, Vitória, ES, Brazil;Programa de Pós-Graduação em Informática, Universidade Federal do Espírito Santo, Vitória, ES, Brazil;Department of Computing, City University, London, UK;Programa de Pós-Graduação em Informática, Universidade Federal do Espírito Santo, Vitória, ES, Brazil
Venue:
ICONIP'06 Proceedings of the 13 international conference on Neural Information Processing - Volume Part I
Year:
2006

Citing 7
Cited 2

The cascade-correlation learning architecture

Advances in neural information processing systems 2
LibGA: a user-friendly workbench for order-based genetic algorithm research

SAC '93 Proceedings of the 1993 ACM/SIGAPP symposium on Applied computing: states of the art and practice
Hypothesis-Driven Constructive Induction in AQ17-HCI: A Method and Experiments

Machine Learning - Special issue on evaluating and changing representation
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
A theoretical and experimental account of n-tuple classifier performance

Neural Computation
Further experimental evidence against the utility of Occam's razor

Journal of Artificial Intelligence Research

Automated multi-label text categorization with VG-RAM weightless neural networks

Neurocomputing
VG-RAM WNN approach to monocular depth perception

ICONIP'10 Proceedings of the 17th international conference on Neural information processing: models and applications - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work, the correlation between input-output patterns stored in the memory of the neurons of Virtual Generalizing RAM (VG-RAM) weightless neural networks, or knowledge correlation, is used to improve the performance of these neural networks. The knowledge correlation, detected using genetic algorithms, is used for changing the distance function employed by VG-RAM neurons in their recall mechanism. In order to evaluate the performance of the method, experiments with several well-known datasets were made. The results showed that VG-RAM networks employing knowledge correlation perform significantly better than standard VG-RAM networks.