비반복적 훈련 신경망을 이용한 숫자인식

Digits Recognition Using a Non-Iterative Neural Network

Most neural network learning schemes are derived from learning systems which are generally iterative in nature. But, when the given input-output training vector pairs satisfy a PLI condition, the training and the application of a hard-limited neural network can be achieved non-iteratively with very short training time and very robust recognition when it is applied to recognize any untrained patterns. In this paper, a method of expanding the dimension of training pattern data is suggested. The proposed method demonstrates better performance and robustness.