Preface CHAPTER 1 Introduction 1.1 Is Pattern Recognition Important? 1.2 Features, Feature Vectors, and Classifiers 1.3 Supervised, Unsupervised, and Semi-Supervised Learning 1.4 MATLAB Programs 1.5 Outline of The BookCHAPTER 2 Classifiers Based on Bayes Decision TheoryCHAPTER 3 Linear ClassifiersCHAPTER 4 Nonlinear ClassifiersCHAPTER 5 Feature SelectionCHAPTER 6 Feature Generation I: Data Transformation and Dimensionality ReductionCHAPTER 7 Feature Generation IICHAPTER 8 Template MatchingCHAPTER 9 Context-Dependent ClassificationCHAPTER 10 Supervised Learning: The EpilogueCHAPTER 11 Clustering: Basic ConceptsCHAPTER 12 Clustering Algorithms I: Sequential AlgorithmsCHAPTER 13 Clustering Algorithms II: Hierarchical AlgorithmsCHAPTER 14 Clustering Algorithms III: Schemes Based on Function OptimizationCHAPTER 15 Clustering Algorithms IVCHAPTER 16 Cluster ValidityAPPENDIX A Hints from Probability and StatisticsAPPENDIX B Linear Algebra BasicsAPPENDIX C Cost Function OptimizationAPPENDIX D Basic Definitions from Linear Systems TheoryIndex
Preface CHAPTER 1 Introduction 1.1 Is Pattern Recognition Important? 1.2 Features, Feature Vectors, and Classifiers 1.3 Supervised, Unsupervised, and Semi-Supervised Learning 1.4 MATLAB Programs 1.5 Outline of The BookCHAPTER 2 Classifiers Based on Bayes Decision TheoryCHAPTER 3 Linear ClassifiersCHAPTER 4 Nonlinear ClassifiersCHAPTER 5 Feature SelectionCHAPTER 6 Feature Generation I: Data Transformation and Dimensionality ReductionCHAPTER 7 Feature Generation IICHAPTER 8 Template MatchingCHAPTER 9 Context-Dependent ClassificationCHAPTER 10 Supervised Learning: The EpilogueCHAPTER 11 Clustering: Basic ConceptsCHAPTER 12 Clustering Algorithms I: Sequential AlgorithmsCHAPTER 13 Clustering Algorithms II: Hierarchical AlgorithmsCHAPTER 14 Clustering Algorithms III: Schemes Based on Function OptimizationCHAPTER 15 Clustering Algorithms IVCHAPTER 16 Cluster ValidityAPPENDIX A Hints from Probability and StatisticsAPPENDIX B Linear Algebra BasicsAPPENDIX C Cost Function OptimizationAPPENDIX D Basic Definitions from Linear Systems TheoryIndex
· · · · · · (收起)
A general principle adopted by most of these techniques is the decomposition of the problem into smaller problems that are easier to handle.
For each smaller problem, a single node is employed. Its parameters are determined either iteratively using appropriate learning algorithms.
From the way these algorithms build the network, they are sometimes referred to as constructive techniques. (查看原文)
The other direction we will follow to design a multilayer perceptron is to fix the architecture and compute its synaptic parameters so as to minimize an appropriate cost function of its output.
This method not only overcomes the drawback of the resulting large networks of the previous section but also makes these networks powerful tools for a number of other applications, beyond pattern recognition.
However, this method is confronted with a serious difficulty. This is discontinuity of the step(activation) function, prohibiting differentiation with respect to the unknown parameters(synaptic weights). (查看原文)
木子三水
电子工业出版社2010版
0 有用 Karl Marx 2019-03-08 13:50:31
非常喜欢的一本书
0 有用 hooliganstreet 2014-03-13 16:28:47
已购
0 有用 Karl Marx 2019-03-08 13:50:31
非常喜欢的一本书
0 有用 hooliganstreet 2014-03-13 16:28:47
已购