Evolutionary Bi-objective Learning with Lowest Complexity in Neural Networks: Empirical Comparisons

Authors:
Yamina Mohamed Ben Ali
Affiliations:
Research Group on Artificial Intelligence, Computer Science Department, Badji Mokhtar University BP 12, Annaba, Algeria
Venue:
ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part I
Year:
2007

Citing 12
Cited 0

Evolving neural networks through augmenting topologies

Evolutionary Computation
ALEC: An Adaptive Learning Framework for Optimizing Artificial Neural Networks

ICCS '01 Proceedings of the International Conference on Computational Science-Part II
From Recombination of Genes to the Estimation of Distributions I. Binary Parameters

PPSN IV Proceedings of the 4th International Conference on Parallel Problem Solving from Nature
The functional localization of neural networks using genetic algorithms

Neural Networks
Structure optimization of neural networks for evolutionary design optimization

Soft Computing - A Fusion of Foundations, Methodologies and Applications
On the Computational Complexity of Binary and Analog Symmetric Hopfield Nets

Neural Computation
An evolutionary machine learning: An adaptability perspective at fine granularity

International Journal of Knowledge-based and Intelligent Engineering Systems
Competitive coevolution through evolutionary complexification

Journal of Artificial Intelligence Research
Pruning neural networks with distribution estimation algorithms

GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI
Optimal design of neural nets using hybrid algorithms

PRICAI'00 Proceedings of the 6th Pacific Rim international conference on Artificial intelligence
On self-adaptive features in real-parameter evolutionary algorithms

IEEE Transactions on Evolutionary Computation
An evolutionary artificial neural networks approach for breast cancer diagnosis

Artificial Intelligence in Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a new study in evolutionary computation technique in order to learn optimal configuration of a multilayer neural network. Inspired from thermodynamic perception, the used evolutionary framework undertakes the optimal configuration problem as a Bi-objective optimization problem. The first objective aims to learn optimal layer topology by considering optimal nodes and optimal connections by nodes. Second objective aims to learn optimal weights setting. The evaluation function of both concurrent objectives is founded on an entropy function which leads the global system to optimal generalization point. Thus, the evolutionary framework shows salient improvements in both modeling and results. The performance of the required algorithms was compared to estimations distribution algorithms in addition to the Backpropagation training algorithm.