MBEANN: mutation-based evolving artificial neural networks

Authors:
Kazuhiro Ohkura;Toshiyuki Yasuda;Yuichi Kawamatsu;Yoshiyuki Matsumura;Kanji Ueda
Affiliations:
Hiroshima University, Higashi-Hiroshima, Japan;Hiroshima University, Higashi-Hiroshima, Japan;Hiroshima University, Higashi-Hiroshima, Japan;Shinshu University, Ueda, Nagano, Japan;The University of Tokyo, Kashiwa, Chiba, Japan
Venue:
ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Year:
2007

Citing 7
Cited 3

Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Evolving neural networks through augmenting topologies

Evolutionary Computation
A comparison between cellular encoding and direct encoding for genetic neural networks

GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation
Competitive coevolution through evolutionary complexification

Journal of Artificial Intelligence Research
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
Solving non-Markovian control tasks with neuroevolution

IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
A new evolutionary system for evolving artificial neural networks

IEEE Transactions on Neural Networks

Neuroevolution with manifold learning for playing Mario

International Journal of Bio-Inspired Computation
Evolving neural fields for problems with large input and output spaces

Neural Networks
Fast learning neural networks using Cartesian genetic programming

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel approach to topology and weight evolving artificial neural networks (TWEANNs) is presented. Compared with previous TWEANNs, this method has two major characteristics. First, a set of genetic operations may be designed without recombination because it often generates an offspring whose fitness value is considerably worse than its parents. Instead, two topological mutations whose effect on fitness value is assumed to be nearly neutral are provided in the genetic operations set. Second, a new encoding technique is introduced to define a string as a set of substrings called operons. To examine our approach, computer simulations were conducted using the standard reinforcement learning problem known as the double pole balancing without velocity information. The results obtained were compared with NEAT results, which is recognised as one of the most powerful techniques in TWEANNs. It was found that our proposed approach yields competitive results, especially when the problem is difficult.