+612 9045 4394
Machine Learning : Discriminative and Generative - Tony Jebara

Machine Learning

Discriminative and Generative

Hardcover Published: 31st December 2003
ISBN: 9781402076473
Number Of Pages: 200

Share This Book:


or 4 easy payments of $59.20 with Learn more
Ships in 7 to 10 business days

Other Available Editions (Hide)

  • Paperback View Product Published: 27th September 2012
    Ships in 7 to 10 business days

Machine Learning: Discriminative and Generative covers the main contemporary themes and tools in machine learning ranging from Bayesian probabilistic models to discriminative support-vector machines. However, unlike previous books that only discuss these rather different approaches in isolation, it bridges the two schools of thought together within a common framework, elegantly connecting their various theories and making one common big-picture. Also, this bridge brings forth new hybrid discriminative-generative tools that combine the strengths of both camps. This book serves multiple purposes as well. The framework acts as a scientific breakthrough, fusing the areas of generative and discriminative learning and will be of interest to many researchers. However, as a conceptual breakthrough, this common framework unifies many previously unrelated tools and techniques and makes them understandable to a larger portion of the public. This gives the more practical-minded engineer, student and the industrial public an easy-access and more sensible road map into the world of machine learning.

Machine Learning: Discriminative and Generative is designed for an audience composed of researchers & practitioners in industry and academia. The book is also suitable as a secondary text for graduate-level students in computer science and engineering.

Industry Reviews

From the reviews:

"This book aims to unite two powerful approaches in machine learning: generative and discriminative. ... Researchers from the generative or discriminative schools will find this book a nice bridge to the other paradigm." (C. Andy Tsao, Mathematical Reviews, Issue 2005 k)

List of Figuresp. ix
List of Tablesp. xi
Prefacep. xiii
Acknowledgmentsp. xvii
Introductionp. 1
Machine Learning Rootsp. 2
Generative Learningp. 5
Generative Models in AIp. 8
Generative Models in Perceptionp. 8
Generative Models in Tracking and Dynamicsp. 9
Why a Probability of Everything?p. 9
Discriminative Learningp. 10
Objectivep. 12
Scope and Organizationp. 14
Online Supportp. 15
Generative Versus Discriminative Learningp. 17
Two Schools of Thoughtp. 18
Generative Probabilistic Modelsp. 19
Discriminative Classifiers and Regressorsp. 21
Generative Learningp. 22
Bayesian Inferencep. 23
Maximum Likelihoodp. 24
The Exponential Familyp. 25
Maximum Entropyp. 28
Expectation Maximization and Mixturesp. 32
Graphical Modelsp. 36
Conditional Learningp. 42
Conditional Bayesian Inferencep. 43
Maximum Conditional Likelihoodp. 46
Logistic Regressionp. 47
Discriminative Learningp. 48
Empirical Risk Minimizationp. 48
Structural Risk Minimizationp. 49
VC Dimension and Large Marginsp. 50
Support Vector Machinesp. 52
Kernel Methodsp. 55
Averaged Classifiersp. 57
Joint Generative-Discriminative Learningp. 58
Maximum Entropy Discriminationp. 61
Regularization Theory and Support Vector Machinesp. 62
Solvabilityp. 64
Support Vector Machines and Kernelsp. 65
A Distribution over Solutionsp. 66
Augmented Distributionsp. 69
Information and Geometry Interpretationsp. 72
Computing the Partition Functionp. 74
Margin Priorsp. 75
Bias Priorsp. 78
Gaussian Bias Priorsp. 78
Non-Informative Bias Priorsp. 78
Support Vector Machinesp. 79
Single Axis SVM Optimizationp. 80
Kernelsp. 81
Generative Modelsp. 81
Exponential Family Modelsp. 82
Empirical Bayes Priorsp. 84
Full Covariance Gaussiansp. 86
Multinomialsp. 91
Generalization Guaranteesp. 93
VC Dimensionp. 93
Sparsityp. 94
PAC-Bayes Boundsp. 95
Extensions to Medp. 99
Multiclass Classificationp. 100
Regressionp. 102
SVM Regressionp. 103
Generative Model Regressionp. 105
Feature Selection and Structure Learningp. 105
Feature Selection in Classificationp. 106
Feature Selection in Regressionp. 110
Feature Selection in Generative Modelsp. 113
Kernel Selectionp. 114
Meta-Learningp. 117
Transductionp. 120
Transductive Classificationp. 121
Transductive Regressionp. 125
Other Extensionsp. 129
Latent Discriminationp. 131
Mixture Models and Latent Variablesp. 133
Iterative MED Projectionp. 137
Bounding the Latent MED Constraintsp. 138
Latent Decision Rulesp. 143
Large Margin Mixtures of Gaussiansp. 144
Parameter Distribution Updatep. 145
Just a Support Vector Machinep. 148
Latent Distributions Updatep. 149
Extension to Kernelsp. 154
Extension to Non Gaussian Mixturesp. 155
Efficiencyp. 155
Efficient Mixtures of Gaussiansp. 160
Structured Latent Modelsp. 161
Factorization of Lagrange Multipliersp. 166
Mean Field for Intractable Modelsp. 168
Conclusionp. 171
A Generative and Discriminative Hybridp. 172
Designing Models versus Designing Kernelsp. 174
What's Next?p. 176
Appendixp. 179
Optimization in the MED Frameworkp. 179
Constrained Gradient Ascentp. 179
Axis-Parallel Optimizationp. 181
Learning Axis Transitionsp. 183
Indexp. 199
Table of Contents provided by Ingram. All Rights Reserved.

ISBN: 9781402076473
ISBN-10: 1402076479
Series: The Springer International Engineering and Computer Science
Audience: General
Format: Hardcover
Language: English
Number Of Pages: 200
Published: 31st December 2003
Country of Publication: US
Dimensions (cm): 24.08 x 16.56  x 1.75
Weight (kg): 0.5