模式识别导论 Pattern Recognition - 武汉大学图像处理与 .ppt

11.6.2 Neuron Model Network Architecture Neuron and transfer function: nnd2n1/2 Training Styles: Incremental Training: “adapt”, the inputs are presented as a cell array of sequential vectors Batch training: : “train”, the inputs are presented as a matrix of concurrent vectors A single neuron cannot do very much. However, several neurons can be combined into a layer or multiple layers that have great power. Toolbox Network Architecture The architecture of a network consists of a description of how many layers a network has, the number of neurons in each layer, each layer’s transfer function, and how the layers connect to each other. The best architecture to use depends on the type of problem to be represented by the network. 6-4-3 Any reasonable function can be represented with a two-layer network: a sigmoid layer feeding a linear output layer. Networks with biases can represent relationships between inputs and outputs more easily than networks without biases. Toolbox 11.6.3 Perceptrons Introduction Neuron Model Perceptron Architecture Learning Rules: perceptron learning rule (learnp) Training Limitations and Cautions Graphical User Interface Summary nnd4db/ nnd4pr ：newp Toolbox 11.6.4 Linear Filters Introduction Neuron Model Perceptron Architecture Learning Rules: LMS Algorithm, Widrow-Hoff learning algorithm (learnwh) Training Limitations and Cautions Summary ：newlin Toolbox 11.6.5 Backpropagation Introduction Model Architecture Training: backpropagation algorithms Faster Training Limitations and Cautions Summary : newff, newrb, newpnn Toolbox 11.6.6 Competitive Network Introduction Competitive Learning Self-Organizing Maps Learning Vector Quantization Networks Summary : newc, newsom, newlvq Toolbox 讨论 人工神经网络是由大量神经元经广泛互联组成的非线性网络，单元间的连接强度从样本中学习 神经网络模型决定于神经元类型，神经元间的连接方式和学习算法 MLP、RBF和SOFM是模式识别中应用最多的几种模型 习题 解释Hebb学习规则的基本思想 浏览Matlab的neural network toolbox的帮助文档（perceptron, linear filter, bp) 写出C-Means算法双层神经网络实现的算法描述或画出流程图 以两类情况为例，证明当神经网络输出采用“c中取1”编码，隐层和输出层神经元均采用Si