Hybrid Evolution of Heterogeneous Neural Networks

Authors:
Zdeněk Buk;Miroslav Šnorek
Affiliations:
Department of Computer Science and Engineering, Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic 121 35;Department of Computer Science and Engineering, Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czech Republic 121 35
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 4
Cited 1

Gradient-based learning algorithms for recurrent networks and their computational complexity

Backpropagation
Handwritten Digit Recognition Using Multi-Layer Feedforward Neural Networks with Periodic and Monotonic Activation Functions

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Introduction to Evolutionary Computing

Introduction to Evolutionary Computing
A learning algorithm for continually running fully recurrent neural networks

Neural Computation

Combining Multiple Inputs in HyperNEAT Mobile Agent Controller

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we are describing experiments and results of applications of the continual evolution algorithm to construction and optimization of recurrent neural networks with heterogeneous units. Our algorithm is a hybrid genetic algorithm with sequential individuals replacement, varibale population size and age-based probability control functions. Short introduction to main idea of the algorithm is given. We describe some new features implemented into the algorithm, the encoding of individuals, crossover, and mutation operators. The behavior of population during an evolutionary process is studied on atificial benchmark data sets. Results of the experiments confirm the theoretical properties of the algorithm.