+612 9045 4394
 
CHECKOUT
Netlab : Algorithms for Pattern Recognition - Ian T. Nabney

Netlab

Algorithms for Pattern Recognition

Paperback Published: 23rd February 2004
ISBN: 9781852334406
Number Of Pages: 420

Share This Book:

Paperback

$135.50
or 4 easy payments of $33.88 with Learn more
Ships in 5 to 9 business days

This volume provides students, researchers and application developers with the knowledge and tools to get the most out of using neural networks and related data modelling techniques to solve pattern recognition problems. Each chapter covers a group of related pattern recognition techniques and includes a range of examples to show how these techniques can be applied to solve practical problems.

Features of particular interest include:


- A NETLAB toolbox which is freely available
- Worked examples, demonstration programs and over 100 graded exercises
- Cutting edge research made accessible for the first time in a highly usable form
- Comprehensive coverage of visualisation methods, Bayesian techniques for neural networks and Gaussian Processes


Although primarily a textbook for teaching undergraduate and postgraduate courses in pattern recognition and neural networks, this book will also be of interest to practitioners and researchers who can use the toolbox to develop application solutions and new models.


..".provides a unique collection of many of the most important pattern recognition algorithms. With its use of compact and easily modified MATLAB scripts, the book is ideally suited to both teaching and research."
Christopher Bishop, Microsoft Research, Cambridge, UK


..".a welcome addition to the literature on neural networks and how to train and use them to solve many of the statistical problems that occur in data analysis and data mining" Jack Cowan, Mathematics Department, University of Chicago, US


"If you have a pattern recognition problem, you should consider NETLAB; if you use NETLAB you must have this book." Keith Worden, University of Sheffield, UK

From the reviews:

..".provides a unique collection of many of the most important pattern recognition algorithms. With its use of compact and easily modified MATLAB scripts, the book is ideally suited to both teaching and research."
Christopher Bishop, Microsoft Research, Cambridge, UK

..".a welcome addition to the literature on neural networks and how to train and use them to solve many of the statistical problems that occur in data analysis and data mining."
Jack Cowan, Mathematics Department, University of Chicago, US

"If you have a pattern recognition problem, you should consider NETLAB; if you use NETLAB you must have this book." Keith Worden, University of Sheffield, UK

"Breezing through the elementary algorithms, Nabney takes readers on a tour of the more sophisticated approaches used by real practitioners. ... It is an invaluable resource for the serious student of neural networks."
David S. Touretzky, Computer Science Department, Carnegie Mellon University, US

"Anyone who intends to use Matlab for pattern recognition and related neural computing applications will benefit from this book. It provides a valuable insight into the methods used within the NETLAB toolbox and serves as a useful reference."
Steve King, Strategic Research Centre, Rolls-Royce plc., UK

"The book aims to provide readers with the knowledge and tools to get the most out of neural networks ... . A series of worked examples and illustrative demonstration programs are also supplied helping the reader to understand the algorithms ... . The book provides an excellent collection of the most important algorithms in pattern recognition. The book can be used as a textbook for teaching undergraduate and postgraduate courses in pattern recognition but it also proves extremely worthy to practitioners and researchers ... ." (Luminita State, Zentralblatt MATH, Vol. 1011, 2003)

"In this book, Ian Nabney provides a well-organized description of NETLAB along with plenty of demonstration programs, worked examples and exercises. ... Throughout the book, the author strictly follows a uniform style in each chapter. ... I think the unification of the style can increase the readability of the book. ... The most benefited readers may be the researchers in the same area. Through this book, they can easily find the algorithms they are interested in and use the algorithms for their own purpose." (Lu Zhang, Expert Update, Vol. 5 (3), 2002)

"The book is solely dedicated to explaining the theoretical background of ... NETLAB. ... mainly presents the algorithms of the functions, their MATLAB program, the formulas used and the required inputs from the users in order to use the functions. ... an excellent list of references is included at the end of the book. ... useful as an illustrative reference when used with the actual software, but also containing enough scientific explanations and theory to be considered a good reference book alone." (Eleazar Jimenez Serrano, IAPR Newsletter, January, 2011)

Introductionp. 1
Introduction to MATLABp. 2
The NETLAB Toolboxp. 18
Worked Example: Data Normalisationp. 29
Parameter Optimisation Algorithmsp. 33
Controlling the Algorithmsp. 34
Quadratic Approximation at a Minimump. 41
Line Searchp. 42
Batch Gradient Descentp. 50
Conjugate Gradientsp. 52
Scaled Conjugate Gradientsp. 56
Quasi-Newton Methodsp. 61
Optimisation and Neural Networksp. 66
Worked Example: Constrained Optimisationp. 71
Density Modelling and Clusteringp. 79
Gaussian Mixture Modelsp. 79
Computing Probabilitiesp. 87
EM Training Algorithmp. 89
Demonstrations of GMMp. 97
K-means Clusteringp. 101
K-nearest-neighbourp. 104
Worked Examplesp. 107
Single Layer Networksp. 117
The Single Layer Feed-forward Networkp. 117
Error Functionsp. 123
Error Gradient Calculationp. 127
Evaluating Other Derivativesp. 128
Iterated Re-weighted Least Squares Trainingp. 132
Demonstration Programsp. 139
Worked Example: Training Regularised Modelsp. 142
The Multi-layer Perceptronp. 149
The Two-layer Feed-forward Networkp. 149
Error Functions and Network Trainingp. 156
Error Gradient Calculationp. 156
Evaluating other Derivativesp. 159
The Hessian Matrixp. 160
Demonstration Programsp. 163
Mixture Density Networksp. 167
Worked Example: Adding Direct Connectionsp. 184
Radial Basis Functionsp. 191
The RBF Networkp. 192
Special Purpose Training Algorithmsp. 199
Error and Error Gradient Calculationp. 203
Evaluating Other Derivativesp. 208
Demonstration Programp. 213
Worked Examples: Linear Smoothingp. 214
Visualisation and Latent Variable Modelsp. 225
Principal Component Analysisp. 226
Probabilistic Principal Component Analysisp. 233
Generative Topographic Mappingp. 243
Topographic Projectionp. 264
Worked Example: Canonical Variatesp. 273
Samplingp. 283
Monte Carlo Integrationp. 284
Basic Samplingp. 285
Markov Chain Samplingp. 290
Demonstration Programsp. 311
Worked Example: Convergence Diagnosticsp. 317
Bayesian Techniquesp. 325
Principles of Bayesian Inferencep. 327
Priors for Neural Networksp. 329
Computing Error and Gradient Functionsp. 337
The Evidence Procedurep. 341
Predictions and Error Barsp. 350
Demonstrations of Evidence Procedurep. 354
Monte Carlo Methodsp. 361
Demonstration of Hybrid Monte Carlo for MLPsp. 362
Worked Example: Improved Classification Approximationp. 364
Gaussian Processesp. 369
Bayesian Regressionp. 369
Theory of Gaussian Processesp. 373
NETLAB Implementationp. 378
Demonstration Programsp. 389
Worked Example: GPs for Classificationp. 392
Linear Algebra and Matricesp. 399
Algorithm Error Analysisp. 403
Referencesp. 407
Function Indexp. 413
Subject Indexp. 416
Table of Contents provided by Blackwell. All Rights Reserved.

ISBN: 9781852334406
ISBN-10: 1852334401
Series: Lecture Notes in Control and Information Sciences
Audience: General
Format: Paperback
Language: English
Number Of Pages: 420
Published: 23rd February 2004
Publisher: Springer London Ltd
Country of Publication: GB
Dimensions (cm): 23.39 x 15.6  x 2.26
Weight (kg): 0.61