A Lamarckian Hybrid of Differential Evolution and Conjugate Gradients for Neural Network Training

Authors:
Krzysztof Bandurski;Wojciech Kwedlo
Affiliations:
Faculty of Computer Science, Bialystok University of Technology, Bialystok, Poland 15-351;Faculty of Computer Science, Bialystok University of Technology, Bialystok, Poland 15-351
Venue:
Neural Processing Letters
Year:
2010

Citing 16
Cited 3

Original Contribution: A scaled conjugate gradient algorithm for fast supervised learning

Neural Networks
Genetic algorithms + data structures = evolution programs (3rd ed.)

Genetic algorithms + data structures = evolution programs (3rd ed.)
Pattern Recognition and Neural Networks

Pattern Recognition and Neural Networks
Evolution strategies –A comprehensive introduction

Natural Computing: an international journal
Differential Evolution – A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces

Journal of Global Optimization
A Lamarckian Approach for Neural Network Training

Neural Processing Letters
Differential Evolution Training Algorithm for Feed-Forward Neural Networks

Neural Processing Letters
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
A Parallel Differential Evolution Algorithm A Parallel Differential Evolution Algorithm

PARELEC '06 Proceedings of the international symposium on Parallel Computing in Electrical Engineering
Comparison of Stochastic Global Optimization Methods to Estimate Neural Network Weights

Neural Processing Letters
Advances in Differential Evolution

Advances in Differential Evolution
Training feedforward neural networks using genetic algorithms

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Differential evolution using a neighborhood-based mutation operator

IEEE Transactions on Evolutionary Computation
Parameter control in evolutionary algorithms

IEEE Transactions on Evolutionary Computation
Self-Adapting Control Parameters in Differential Evolution: A Comparative Study on Numerical Benchmark Problems

IEEE Transactions on Evolutionary Computation
A new evolutionary system for evolving artificial neural networks

IEEE Transactions on Neural Networks

Neuro-logistic Models Based on Evolutionary Generalized Radial Basis Function for the Microarray Gene Expression Classification Problem

Neural Processing Letters
Adaptive Memetic Differential Evolution with Global and Local neighborhood-based mutation operators

Information Sciences: an International Journal
Comparing large number of metaheuristics for artificial neural networks training to predict water temperature in a natural river

Computers & Geosciences

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper describes two schemes that follow the model of Lamarckian evolution and combine differential evolution (DE), which is a population-based stochastic global search method, with the local optimization algorithm of conjugate gradients (CG). In the first, each offspring is fine-tuned by CG before competing with their parents. In the other CG is used to improve both parents and offspring in a manner that is completely seamless for individuals that survive more than one generation. Experiments involved training weights of feed-forward neural networks to solve three synthetic and four real-life problems. In six out of seven cases the DE---CG hybrid, which preserves and uses information on each solution's local optimization process, outperformed two recent variants of DE.