Evolving Chaotic Neural Network for Creative Sequence Generation
p. 185-195
Résumé
This paper describes an approach to generate a sequence requiring an unrealizable function by programs, such as a flash that is required especially in creative activity of a human. We have already proposed a recurrent neural network that demonstrates a generation of several creative sequences, but convergency and stability problems occur. On the other hand, it is known in biological experiments where the chaotic sequences can be observed from brain waves. The neural network constructed from chaotic neurons has nonlinear dynamics, but there remains the difficulty of training method. We propose an evolutional methodology to train a chaotic neural network, and introduce Darwinism for its evolving process. To determine their most suitable structure and the weights of connection, we use AIC for the fitness value.
Index
Texte
Citer cet article
Référence papier
Shunji Kawabata, Keiichi Sakai et Tadashi Ae, « Evolving Chaotic Neural Network for Creative Sequence Generation », CASYS, 14 | 2004, 185-195.
Référence électronique
Shunji Kawabata, Keiichi Sakai et Tadashi Ae, « Evolving Chaotic Neural Network for Creative Sequence Generation », CASYS [En ligne], 14 | 2004, mis en ligne le 29 August 2024, consulté le 20 September 2024. URL : http://popups.lib.uliege.be/1373-5411/index.php?id=2605
Auteurs
Shunji Kawabata
Graduate School of Engineering, Hiroshima University 1-4- 1 Kagamiyama, Higashi-Hiroshima, 739-8527 Japan
Keiichi Sakai
Graduate School of Engineering, Hiroshima University 1-4- 1 Kagamiyama, Higashi-Hiroshima, 739-8527 Japan
Tadashi Ae
Graduate School of Engineering, Hiroshima University 1-4- 1 Kagamiyama, Higashi-Hiroshima, 739-8527 Japan