Evolving Product Unit Neural Networks with Particle Swarm Optimization
- Resource Type
- Conference
- Authors
- Huang, Rong; Tong, Shurong
- Source
- 2009 Fifth International Conference on Image and Graphics Image and Graphics, 2009. ICIG '09. Fifth International Conference on. :624-628 Sep, 2009
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Neural networks
Particle swarm optimization
Neurons
Management training
Training data
Signal processing
Backpropagation algorithms
Genetic algorithms
Graphics
Computer network management
- Language
Product unit neural network (PUNN) training is formulated as an optimization problem and then particle swarm optimization (PSO), an emerging evolutionary computation algorithm, is employed to resolve it. A simple and effective encoding scheme for particles is proposed by which PSO algorithm can configure the architecture and weight of PUNN simultaneously depending on training sets. Because the training algorithm takes into account not only network error but also the complexity of network, the resulting networks alleviate over-fitting. Experimental results show that proposed algorithm achieves rational architecture for PUNN networks and the resulting networks obtain strong generalization abilities.