Evolutionary design of neural networks has shown a great potential as a powerful optimization tool. However, most evolutionary neural networks have not taken advantage of the fact that they can evolve from modules. This paper presents a hybrid method of modular neural networks and genetic programming as a promising model for evolutionary learning. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which might not only develop new functionality spontaneously, but also grow and evolve its own structure autonomously. We show the potential of the method by applying an evolved modular network to a visual categorization task with handwritten digits. Sophisticated network architectures as well as functional subsystems emerge from an initial set of randomly-connected networks. Moreover, the evolved neural network has reproduced some of the characteristics of natural visual system, such as the organization of coarse and fine processing of stimuli in separate pathways.
Bibliographical noteFunding Information:
The author would like to thank Dr. Y. Tohkura at ATR HIP laboratories for continuous encouragement. This work was supported in part by a grant no. 961-0901-009-2 from the Korea Science and Engineering Foundation (KOSEF) and a grant no. SC-13 from the Ministry of Science and Technology in Korea.
All Science Journal Classification (ASJC) codes
- Artificial Intelligence