A GA-based flexible learning algorithm with error tolerance for digital binary neural networks
- Resource Type
- Conference
- Authors
- Kabeya, Shutaro; Abe, Tohru; Saito, Toshimichi
- Source
- 2009 International Joint Conference on Neural Networks Neural Networks, 2009. IJCNN 2009. International Joint Conference on. :1476-1480 Jun, 2009
- Subject
- Computing and Processing
Communication, Networking and Broadcast Technologies
Neural networks
Signal processing algorithms
Neurons
Boolean functions
Approximation algorithms
Genetic algorithms
Noise reduction
Nonlinear dynamical systems
USA Councils
Algorithm design and analysis
- Language
- ISSN
- 2161-4393
2161-4407
This paper presents a learning algorithm of digital binary neural networks for approximation of desired Boolean functions. In the learning, the genetic algorithms is used with flexible fitness that tolerates error: it is suitable to reduce the number of hidden neurons and to tolerate noise and outliers. We then apply the algorithm to design of cellular automata with rich spatio-temporal patterns and various applications. Performing basic numerical experiment, the algorithm efficiency is confirmed.