ラテン文字認識するための自己発生適応共鳴理-1(ART-1)ニューラル・ネットワーク

概要

論文の詳細を見る
This study presents a self-generation ART-1 neural network, an efficient algorithm that emulates the self-organizing pattern recognition developed to avoid the stability-plasticity dilemma in competitive networks learning for Latin alphabet recognition to use in a vision system for road signs recognition. The first step of our approach deals with the training process where a set of input vectors are presented sequentially to the preprocessor to specify the inputs for the networks. Secondly the value of the mean squared error is used to measure the candidate for the output in the recognition phase. Thirdly to move down the large error-surface created by delta rule during the search phase the gradient-descent is used by changing each of the weights by an amount that is proportional to the negative of the slope. In the simulation test our system can self organize in real time producing stable recognition while getting inputs pattern beyond those originally stored. Its can also preserve its previously learned knowledge while keeping its ability to learn new pattern. A parameter called the attentional vigilance parameter determines how fine the categories will be.