Neural Network Research Using Particle Swarm Optimization
- Resource Type
- Conference
- Authors
- Wang, Yahui; Xia, Zhifeng; Huo, Yifeng
- Source
- 2011 International Conference on Internet Computing and Information Services Internet Computing & Information Services (ICICIS), 2011 International Conference on. :407-410 Sep, 2011
- Subject
- Computing and Processing
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Particle swarm optimization
Training
Algorithm design and analysis
Educational institutions
Optimization
Signal processing algorithms
Testing
Two-layer Particle Swarm
Neural network
Regularization
- Language
In view of the artificial neural network weights training problem, this paper proposed a method to optimize the network's structure parameters and regularization coefficient using two-layer Particle Swarm Optimization (PSO). This algorithm was applied to train Adaline network. Compared with fixed regularization coefficient method and Sliding Mode Variable Structure optimization method, the result showed that it had the advantages of high precision and strong ability of generalization.