人工神经网络3 研究生现代控制工程教案 人工智能控制 教学讲义.pptVIP

第八章 人工神经网络 * 模式识别导论Pattern Recognition 第八章 人工神经网络竞争学习、自组织特征映射 王文伟 Wang Wenwei, Dr.-Ing. Tel: 687-78652 Email: wwwang@ Web: /sites/ced/pr/ 电子信息学院 Table of Contents 电子信息学院 1. Introduction Self-organizing in networks is one of the most fascinating topics in the neural network field. Such networks can learn to detect regularities and correlations in their input and adapt their future responses to that input accordingly. The neurons of competitive networks learn to recognize groups of similar input vectors (clustering). 2. Competitive networks wkj k j The ||dist|| box: 竞争网络 侧向抑制性连接 输出神经元之间有侧向抑制性连接，较强单元获胜并抑制其他单元，独处激活状态（Winner takes all, WTA） 竞争网络 wkj ok j netk x 竞争网络举例 Suppose we want to divide the following four two-element vectors into two classes.p = [.1 .8 .1 .9; .2 .9 .1 .8]  p = 0.1000 0.8000 0.1000 0.9000 0.2000 0.9000 0.1000 0.8000 create a network：net = newc([0 1; 0 1],2); Training：net.trainParam.epochs = 500net = train(net,p); During each epoch, a single vector is chosen randomly and presented to the network and weight and bias values are updated accordingly. 竞争网络 竞争网络举例 Simulate the network, and finally convert its output vectors to class indices.a = sim(net,p);ac = vec2ind(a) ac = 1 2 1 2 Graphical example: democ1 竞争网络 第八章 人工神经网络 *