A Novel Spatial Architecture Artificial Neural Network Based on Multilayer Feedforward Network with Mutual Inhibition among Hidden Units

摘要

We propose a Spatial Artificial Neural Network (SANN) with spatial architecture which consists of a multilayer feedforward neural network with hidden units adopt recurrent lateral inhibition connection, all input and hidden neurons have synapses connections with the output neurons. In addition, a supervised learning algorithm based on error back propagation is developed. The proposed network has shown a superior generalization capability in simulations with pattern recognition and non-linear function approximation problems. And, the experimental also shown that SANN has the capability of avoiding local minima problem.