Abstract:
The problem of unsupervised and supervised learning
of RBF networks is discussed with Multi-Objective Particle Swarm Optimization
(MOPSO). This study presents an evolutionary multi-objective selection
method of RBF networks structure. The candidates of RBF networks structures
are encoded into particles in PSO. These particles evolve toward Pareto-optimal
front defined by several objective functions with model accuracy and complexity.
This study suggests an approach of RBF network training through simultaneous
optimization of architectures and connections with PSO-based multi-objective
algorithm. Present goal is to determine whether MOPSO can train RBF networks
and the performance is validated on accuracy and complexity. The experiments
are conducted on two benchmark datasets obtained from the machine learning
repository. The results show that; the best results are obtained for our
proposed method that has obtained 100 and 80.21% classification accuracy
from the experiments made on the data taken from breast cancer and diabetes
diseases database, respectively. The results also show that our approach
provides an effective means to solve multi-objective RBF networks and
outperforms multi-objective genetic algorithm.
S.N. Qasem and S.M. Shamsuddin, 2010. Generalization Improvement of Radial Basis Function Network Based on Multi-Objective Particle Swarm Optimization. Journal of Artificial Intelligence, 3: 1-16.
Subscribe Today 
