NEURAL NETWORK TRAINING WITH PARALLEL PARTICLE SWARM OPTIMIZER / 药物分析学报
Journal of Pharmaceutical Analysis
;
(6): 109-112, 2006.
Article
in Chinese
| WPRIM
| ID: wpr-621759
ABSTRACT
Objective To reduce the execution time of neural network training. Methods Parallel particle swarm optimization algorithm based on master-slave model is proposed to train radial basis function neural networks, which is implemented on a cluster using MPI libraries for inter-process communication. Results High speed-up factor is achieved and execution time is reduced greatly. On the other hand, the resulting neural network has good classification accuracy not only on training sets but also on test sets. Conclusion Since the fitness evaluation is intensive, parallel particle swarm optimization shows great advantages to speed up neural network training.
Full text:
Available
Index:
WPRIM (Western Pacific)
Type of study:
Prognostic study
Language:
Chinese
Journal:
Journal of Pharmaceutical Analysis
Year:
2006
Type:
Article
Similar
MEDLINE
...
LILACS
LIS