Bishop的成名作（1995）：Neural Networks for Pattern Recognition

相似文件 换一批

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

<p>Bishop的成名作（1995）：Neural Networks for Pattern Recognition</p><p> 193938.pdf (22.44 MB, 需要: 25 个论坛币)

2008-2-23 19:30:00 上传

Bishop的成名作（1995）：Neural Networks for Pattern Recognition
需要: 25 个论坛币  [购买]

<br/></p><p>CONTENTS<br/>1 Statistical Pattern Recognition 1<br/>1.1 An example - character recognition 1<br/>1.2 Classification and regression 5<br/>1.3 Pre-processing and feature extraction 6<br/>1.4 The curse of dimensionality 7<br/>1.5 Polynomial curve fitting 9<br/>1.6 Model complexity 14<br/>1.7 Multivariate non-linear functions 15<br/>1.8 Bayes' theorem 17<br/>1.9 Decision boundaries 23<br/>1.10 Minimizing risk 27<br/>Exercises - - 28<br/>2 Probability Density Estimation 33<br/>2.1 Parametric methods 34<br/>2.2 Maximum likelihood 39<br/>2.3 Bayesian inference 42<br/>2.4 Sequential parameter estimation 46<br/>2.5 Non-parametric methods 49<br/>2.6 Mixture models 59<br/>Exercises 73<br/>3 Single-Layer Networks 77<br/>3.1 Linear discriminant functions 77<br/>3.2 Linear separability 85<br/>3.3 Generalized linear discriminants 88<br/>3.4 Least-squares techniques 89<br/>3.5 The perceptron 98<br/>3.6 Fisher's linear discriminant 105<br/>Exercises 112<br/>4 The Multi-layer Perceptron • 116<br/>4.1 Feed-forward network mappings 116<br/>4.2 Threshold units 121<br/>4.3 Sigmoidal units 126<br/>4.4 Weight-space symmetries 133<br/>4.5 Higher-order networks 133<br/>4.6 Projection pursuit regression 135<br/>4.7 Kolmogorov's theorem 137<br/>xvi Contents<br/>4.8 Error back-propagation 140<br/>4.9 The Jacobian matrix 148<br/>4.10 The Hessian matrix 150<br/>Exercises 161<br/>5 Radial Basis Functions 164<br/>5.1 Exact interpolation 164<br/>5.2 Radial basis function networks 167<br/>5.3 Network training 170<br/>5.4 Regularization theory 171<br/>5.5 Noisy interpolation theory 176<br/>5.6 Relation to kernel regression 177<br/>5.7 Radial basis function networks for classification 179<br/>5.8 Comparison with the multi-layer perceptron 182<br/>5.9 Basis function optimization 183<br/>5.10 Supervised training 190<br/>Exercises 191<br/>6 Error Functions 194<br/>6.1 Sum-of-squares error 195<br/>6.2 Minkowski error 208<br/>6.3 Input-dependent variance 211<br/>6.4 Modelling conditional distributions 212<br/>6.5 Estimating posterior probabilities 222<br/>6.6 Sum-of-squares for classification 225<br/>6.7 Cross-entropy for two classes 230<br/>6.8 Multiple independent attributes 236<br/>6.9 Cross-eutropy for multiple classes 237<br/>6.10 Entropy 240<br/>6.11 General conditions for outputs to be probabilities 245<br/>Exercises 248<br/>7 Parameter Optimization Algorithms 253<br/>7.1 Error surfaces 254<br/>7.2 Local quadratic approximation 257<br/>7.3 Linear output units 259<br/>7.4 Optimization in practice 260<br/>7.5 Gradient descent 263<br/>7.6 Line search 272<br/>7.7 Conjugate gradients 274<br/>7.8 Scaled conjugate gradients 282<br/>7.9 Newton's method 285<br/>7.10 Quasi-Newton methods 287<br/>7.11 The Levenberg-Marquardt; algorithm 290<br/>Exercises 292<br/>Contents xvii<br/>8 Pre-processing and Feature Extraction 295<br/>8.1 Pre-processing and post-processing 296<br/>8.2 Input normalization and encoding 298<br/>8.3 Missing data 301<br/>8.4 Time series prediction 302<br/>8.5 Feature selection 304<br/>8.6 Principal component analysis 310<br/>8.7 Invariances and prior knowledge 319<br/>Exercises 329<br/>9 Learning and Generalization 332<br/>9.1 Bias and variance 333<br/>9.2 Regularization 338<br/>9.3 Training with noise 346<br/>9.4 Soft weight sharing 349<br/>9.5 Growing and pruning algorithms 353<br/>9.6 Committees of networks 364<br/>9.7 Mixtures of experts 369<br/>9.8 Model order selection 371<br/>9.9 Vapnik-Chervonenkis dimension 377<br/>Exercises , 380<br/>10 Bayesian Techniques 385<br/>10.1 Bayesian learning of network weights 387<br/>10.2 Distribution of network outputs 398<br/>10.3 Application to classification problems 403<br/>10.4 The evidence framework for a and /3 406<br/>10.5 Integration over hyperparameters 415<br/>10.6 Bayesian mode! comparison 418<br/>10.7 Committees of networks 422<br/>10.8 Practical implementation of Bayesian techniques 424<br/>10.9 Monte Carlo methods 425<br/>10.10 Minimum description length 429<br/>Exercises 433<br/>A Symmetric Matrices 440<br/>B Gaussian Integrals 444<br/>C Lagrange Multipliers 448<br/>D Calculus of Variations 451<br/>E Principal Components 454<br/>References 457<br/>Index 477</p>

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏2 回帖

关键词：Recognition cognition Networks network Pattern complexity character example methods

偶的现金不够

楼主好人，能否帮帮忙？万分感谢 

raushon@126.com

我来给个详细介绍

【书名】 Neural Networks for Pattern Recognition
【作者】CHRISTOPHER M. BISHOP
【出版社】Oxford University Press
【版本】
【出版日期】1996
【文件格式】PDF
【文件大小】22.4 MB
【页数】504 Pages
【ISBN出版号】ISBN-10: 0198538642 ISBN-13: 978-0198538646
【资料类别】计量经济学，统计学，
【市面定价】82.80 Dollars (Amazon Paperback)
【扫描版还是影印版】影印版
【是否缺页】完整
【关键词】Neutral Nwtwork, target coding scheme, logistic sigmoid activation function, outer product approximation, Monte Carlo
【内容简介】

This book provides a solid statistical foundation for neural networks from a pattern recognition perspective. The focus is on the types of neural nets that are most widely used in practical applications, such as the multi-layer perceptron and radial basis function networks. Rather than trying to cover many different types of neural networks, Bishop thoroughly covers topics such as density estimation, error functions, parameter optimization algorithms, data pre-processing, and Bayesian methods. All topics are organized well and all mathematical foundations are explained before being applied to neural networks. The text is suitable for a graduate or advanced undergraduate level course on neural networks or for practitioners interested in applying neural networks to real-world problems. The reader is assumed to have the level of math knowledge necessary for an undergraduate science degree.

【目录】

CONTENTS
1 Statistical Pattern Recognition 1
2 Probability Density Estimation 33
3 Single-Layer Networks 77
4 The Multi-layer Perceptron • 116
5 Radial Basis Functions 164
6 Error Functions 194
7 Parameter Optimization Algorithms 253
8 Pre-processing and Feature Extraction 295
9 Learning and Generalization 332
10 Bayesian Techniques 385

【书评】很不错的书，看目录就知道

...............

mei xian jin a a~~~

xdsdsdsdsdsdsdss

1# prestige
you have already so much money ,why are you still asking for so much for the materials?

楼主能发给我一份吗？lishufox@hotmail.com

第一次回帖,献给lz的好书

好书，不过确实也有些贵