Optimizing the Performance of Probabilistic Neural Networks in a Bioinformatics Task

A self adaptive probabilistic neural network model is proposed. The model incorporates the Particle Swarm Optimization algorithm to optimize the spread parameter of the probabilistic neural network, enhancing thus its performance. The proposed approach is tested on two data sets from the field of bioinformatics, with promising results. The performance of the proposed model is compared to probabilistic neural networks, as well as to four different feedforward neural networks. Different sampling techniques are used, and statistical tests are performed to justify the statistical significance of the results.