Well-trained neural networks have low sensitivity to input errors. Also, the sensitivity to weigh errors must be considered when implementing neural networks with hardware of limited precision. In this paper, we derive the sensitivity of the Madaline to weight perturbation or input errors in terms of the trained weights, the input pattern, and the variance of weight perturbation or the probability of input errors. The result is verified with a simulation of the Madaline recognizing handwritten digits.
DOI 인용 스타일