Spike Neural Network Learning Algorithm Based on an Evolutionary Membrane Algorithm

As one of the important artificial intelligence fields, brain-like computing attempts to give machines a higher level by studying and simulating cognitive principles human brain. Compared with traditional neural network, spiking network (SNN) has better biogenesis stronger power. In this paper, an SNN learning model based on evolutionary membrane algorithm is proposed solve problem supervised classification. The uses P system's object, reaction rules, structure these problems. Specifically, can automatically adjust parameters adjusting synaptic weight in stage according different application data, providing solution for balance exploration exploitation. simulation experiment, effectiveness verification research carried out. results show that compared other experimental algorithms, competitive advantage solving twelve classification benchmark problems through curves quantified results.