Abstract
Abstract: The TAM (Topographic Attentive Mapping) Network based on a biologically-motivated neural network is an especially effective model. When the network makes an incorrect output prediction, the attentional feedback circuit modulates the learning rates, and adds a node to the category layer in order to improve the network's prediction accuracy. In this paper, Gabor type receptive field is formulated in the input layer of TAM network. By using Gabor filtering, we can detect orientation selectivity of visual images, and simulate the mechanism of early vision of brain as a computational model.
