Multi-Layer Perceptron Decided Leaning Neurons by Regular Output Glias

A glia is nervous cell which is existing in a brain. This cell changes a Ca2+ concentration and this ion affects a neuron learning. In the biological system, when the glia does not increase the Ca2+ concentration, the neuron cannot increase the response. From these features, we propose a Multi-Layer Perceptron (MLP) decided learning neurons by regular output glias. The neurons are separated to some groups. Each group changes a learning term and a non-learning term. We consider that a performance of the MLP improves by having two terms. By two different simulations, we confirm a learning ability and a characteristics of the proposed MLP.