Extracting rules from fuzzy neural network by particle swarm optimisation

A four layer fuzzy neural network is presented to realise knowledge acquisition from input-output samples. The network parameters including the necessary membership functions of the input variables and the consequent parameters are tuned and identified using a modified particle swarm algorithm which uses each particle's best current performance of its neighbours to replace the best previous one and uses a non accumulative rate of change to replace the accumulative one for accelerating search procedure. The trained network is then pruned so that the general rules can be extracted and explained. The experimental results have shown that the similar classification rules can be obtained in comparison to that of other fuzzy neural approaches.