模式识别11-竞争学习-SOM-LVQ.pptxVIP

电子信息学院IPL模式识别与神经网络Pattern Recognition and Neural Network第11章 人工神经网络竞争学习、自组织特征映射、学习向量量化 王文伟 Wang Wenwei, Dr.-Ing.Tel: mail: wwwang@Web: /sites/ced/prnn/电子信息学院Table of Contents1. IntroductionThe neurons of competitive networks learn to recognize groups of similar input vectors (clustering).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.wkjkj竞争网络2. Competitive networks输出神经元之间有侧向抑制性连接，引进竞争机制（神经元激活自己而抑制其他），实现无监督学习。xokwkjnetkj侧向抑制性连接竞争网络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）wkjkj竞争网络的简化结构竞争网络The compet transfunc.The ||dist|| box:权值的学习规则（竞争学习）竞争网络Demo: nnd14clThe competitive network learns to categorize the input vectors.Kohonen Learning Rule (learnk) :Every cluster of similar input vectors will have a neuron that outputs 1 when a vector in the cluster is presented.Bias Learning Rule竞争网络Dead neurons： some neurons may never win the competition. These unfortunate neurons never perform a useful function.Bias Learning Rule (learncon)：biases of neurons that haven’t responded very frequently will increase versus biases of neurons that have responded frequently.Biases give neurons that only win the competition rarely an advantage over neurons that win often. 竞争网络举例竞争网络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 0.8000create 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.竞争网络举例竞争网络Simulate the network, and finally convert its output vectors to class indices.a = sim(net,p);ac = vec2ind(a)ac = 1 2 1 2 p = 0.1000 0.8000 0.1000 0.9000 0.2000 0.9000 0.1000 0.80