Improved Fuzzy Single Layer Supervised Learning Algorithm
Jongchan Kim, Kyeong-Jin Ban, Eung-Kon Kim, An-Suk Oh, Yang Sun Lee · 2011
In this paper, we improve the convergence prevented from vibrating decision boundary with bias term and suggest a linear activation function. We propose an enhanced fuzzy single layer perceptron which reduces the learning time introducing the rate of learning and the concept of momentum. We applied to Exclusive OR problem and pattern recognition of letters to analyze the performance of learning through enhanced fuzzy single layer perceptron and precedent fuzzy single layer perceptron. After the number of epoch and the convergence of enhanced fuzzy single layer perceptron were compared with those of precedent one, we found that enhanced one had far less time for learning and improved the convergence.