A new particle swarm optimization algorithm for neural network optimization
This paper presents a new particle swarm optimization (PSO) algorithm for tuning parameters (weights) of neural networks. The new PSO algorithm is called fuzzy logic-based particle swarm optimization with cross-mutated operation (FPSOCM), where the fuzzy inference system is applied to determine the...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
IEEE Computer Society
2009
|
| Online Access: | http://hdl.handle.net/20.500.11937/15919 |
| _version_ | 1848749025926316032 |
|---|---|
| author | Ling, S. Nguyen, H. Chan, Kit Yan |
| author2 | Wanlei Zhou |
| author_facet | Wanlei Zhou Ling, S. Nguyen, H. Chan, Kit Yan |
| author_sort | Ling, S. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This paper presents a new particle swarm optimization (PSO) algorithm for tuning parameters (weights) of neural networks. The new PSO algorithm is called fuzzy logic-based particle swarm optimization with cross-mutated operation (FPSOCM), where the fuzzy inference system is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation by using human knowledge. By introducing the fuzzy system, the value of the inertia weight becomes variable. The cross-mutated operation is effectively force the solution to escape the local optimum. Tuning parameters (weights) of neural networks is presented using the FPSOCM. Numerical example of neural network is given to illustrate that the performance of the FPSOCM is good for tuning the parameters (weights) of neural networks. |
| first_indexed | 2025-11-14T07:14:23Z |
| format | Conference Paper |
| id | curtin-20.500.11937-15919 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T07:14:23Z |
| publishDate | 2009 |
| publisher | IEEE Computer Society |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-159192017-10-02T02:27:09Z A new particle swarm optimization algorithm for neural network optimization Ling, S. Nguyen, H. Chan, Kit Yan Wanlei Zhou This paper presents a new particle swarm optimization (PSO) algorithm for tuning parameters (weights) of neural networks. The new PSO algorithm is called fuzzy logic-based particle swarm optimization with cross-mutated operation (FPSOCM), where the fuzzy inference system is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation by using human knowledge. By introducing the fuzzy system, the value of the inertia weight becomes variable. The cross-mutated operation is effectively force the solution to escape the local optimum. Tuning parameters (weights) of neural networks is presented using the FPSOCM. Numerical example of neural network is given to illustrate that the performance of the FPSOCM is good for tuning the parameters (weights) of neural networks. 2009 Conference Paper http://hdl.handle.net/20.500.11937/15919 IEEE Computer Society fulltext |
| spellingShingle | Ling, S. Nguyen, H. Chan, Kit Yan A new particle swarm optimization algorithm for neural network optimization |
| title | A new particle swarm optimization algorithm for neural network optimization |
| title_full | A new particle swarm optimization algorithm for neural network optimization |
| title_fullStr | A new particle swarm optimization algorithm for neural network optimization |
| title_full_unstemmed | A new particle swarm optimization algorithm for neural network optimization |
| title_short | A new particle swarm optimization algorithm for neural network optimization |
| title_sort | new particle swarm optimization algorithm for neural network optimization |
| url | http://hdl.handle.net/20.500.11937/15919 |