神经网络

Foreword PrefacMore Acknowledgements Part Ⅰ　Traces of History and A Neuroscience Briefer 　1. Brain Style Computing: Origins and Issues 　　1.1 From the Greeks to the Renaissance 　　1.2 The Advent of Modern Neuroscience 　　1.3 On the Road to Artificial Intelligence 　　1.4 Classical AI and Neural Networks 　　1.5 Hybrid Intelligent Systems 　　　Chapter Summary 　　　Bibliographic Remarks 　2. Lessons from Neuroscience 　　2.1 The Human Brain 　　2.2 Biological Neurons

Foreword PrefacMore Acknowledgements Part Ⅰ　Traces of History and A Neuroscience Briefer 　1. Brain Style Computing: Origins and Issues 　　1.1 From the Greeks to the Renaissance 　　1.2 The Advent of Modern Neuroscience 　　1.3 On the Road to Artificial Intelligence 　　1.4 Classical AI and Neural Networks 　　1.5 Hybrid Intelligent Systems 　　　Chapter Summary 　　　Bibliographic Remarks 　2. Lessons from Neuroscience 　　2.1 The Human Brain 　　2.2 Biological Neurons 　　　Chapter Summary　　　Bibliographic Remarks Part Ⅱ　Feedforward Neural Networks and Supervised Learning 　3. Artificial Neurons, Neural Networks and Architectures 　　3.1　Neuron Abstraction 　　3.2 Neuron Signal Functions 　　3.3 Mathematical Preliminaries 　　3.4 Neural Networks Defined 　　3.5 Architectures: Feedforward and Feedback 　　3.6 Salient Properties and Application Domains of Neural Networks 　　　Chapter Summary 　　　Bibliographic Remarks 　　　Review Questions　4. Geometry of Binary Threshold Neurons and Their Networks 　　4.1 Pattern Recognition and Data Classification 　　4.2 Convex Sets, Convex Hulls and Linear Separability 　　4.3 Space of Boolean Functions 　　4.4 Binary Neurons are Pattern Dichotomizers 　　4.5 Non-linearly Separable Problems 　　4.6 Capacity of a Simple Threshold Logic Neuron 　　4.7 Revisiting the XOR Problem 　　4.8 Multilayer Networks 　　4.9 How Many Hidden Nodes are Enough? 　　　Chapter Summary 　　　Bibliographic Remarks 　　　Review Questions 　5. Supervised LearningⅠ: Perceptrons and LMS 　　5.1 Learning and Memory 　　5.2 From Synapses to Behaviour: The Case of Aplysia　　5.3 Learning Algorithms 　　5.4 Error Correction and Gradient Descent Rules 　　5.5 The Learning Objective for TLNs 　　5.6 Pattern Space and Weight Space 　　5.7 Perceptron Learning Algorithm 　　5.8 Perceptron Convergence Theorem　　5.9 A Handworked Example and MATLAB Simulation 　　5.10 Perceptron Learning and Non-separable Sets 　　5.11 Handling Linearly Non-separable Sets 5.12 a–Least Mean Square Learning 5.13 MSE Error Surface and its Geometry 　　5.14 Steepest Descent Search with Exact Gradient Information 5.15 u–LMS: Approximate Gradient Descent 5.16 Application of LMS to Noise Cancellation 　　　Chapter Summary 　　　Bibliographic Remarks 　　　Review Questions 　6. Supervised Learning Ⅱ: Backpropagation and Beyond 　　6.1 Multilayered Network Architectures 　　6.2 Backpropagation Learning Algorithm 　　6.3 Handworked Example 　　6.4 MATLAB Simulation Examples 　　6.5 Practical Considerations in Implementing the BP Algorithm 　　6.6 Structure Growing Algorithms 　　6.7 Fast Relatives of Backpropagation 　　6.8 Universal Function Approximation and Neural Networks 　　6.9 Applications of Feedforward Neural Networks　　6.10 Reinforcement Learning: A Brief Review 　　　Chapter Summary 　　　Bibliographic Remarks 　　　Review Questions 　7. Neural Networks: A Statistical Pattern Recognition Perspective 　　7.1 Introduction 　　7.2 Bayes’ Theorem 　　7.3 Two Instructive MATLAB Simulations 　　7.4 Implementing Classification Decisions with Bayes’ Theorem 　　7.5 Probabilistic Interpretation of a Neuron Discriminant Function 　　7.6 MATLAB Simulation: Plotting Bayesian Decision Boundaries 　　7.7 Interpreting Neuron Signals as Probabilities　　7.8 Multilayered Networks, Error Functions and Posterior Probabilities 　　7.9 Error Functions for Classification Problems 　　　Chapter Summary 　　　Bibliographic Remarks 　　　Review Questions 　8. Focussing on Generalization: Support Vector Machines and Radial Basis Function Networks 　　8.1 Learning From Examples and Generalization 　　8.2 Statistical Learning Theory Briefer 　　8.3 Support Vector Machines　　8.4 Radial Basis Function Networks 　　8.5 Regularization Theory Route to RBFNs　　8.6 Generalized Radial Basis Function Network 　　8.7 Learning in RBFN’s 　　8.8 Image Classification Application 　　8.9 Other Models For Valid Generalization　　　Chapter Summary 　　　Bibliographic Remarks 　　　Review Questions Part Ⅲ Recurrent Neurodynamical Systems Part Ⅳ　 Contemporary Topics Appendix A: Neural Network Hardware Appendix B: Web Pointers Bibliography Index

本书从理论和实际应用出发，全面系统地介绍神经网络的基本模型、基本方法和基本技术，涵盖了神经系统科学、统计模式识别、支撑向量机、模糊系统、软件计算与动态系统等内容。本书对神经网络的各种基本模型做了深入研究，对神经网络的最新发展趋势和主要研究方向也都进行了全面而综合的介绍，每章都包含大量例题、习题，对所有模型不仅给出了实际的应用示例，还提供了详细的MATHLAB代码，是一本很好的神经网络教材。 本书适合作为相关专业研究生或本科高年级学生的教材，也是神经网络的科研人员的参考书。