- Title Pages
- Series Foreword
- Preface
-
1 Introduction to Semi-Supervised Learning -
1 A Taxonomy for Semi-Supervised Learning Methods -
3 Semi-Supervised Text Classification Using EM -
4 Risks of Semi-Supervised Learning: How Unlabeled Data Can Degrade Performance of Generative Classifiers -
5 Probabilistic Semi-Supervised Clustering with Constraints -
6 Transductive Support Vector Machines -
7 Semi-Supervised Learning Using Semi-Definite Programming -
8 Gaussian Processes and the Null-Category Noise Model -
9 Entropy Regularization -
10 Data-Dependent Regularization -
11 Label Propagation and Quadratic Criterion -
12 The Geometric Basis of Semi-Supervised Learning -
13 Discrete Regularization -
14 Semi-Supervised Learning with Conditional Harmonic Mixing -
15 Graph Kernels by Spectral Transforms -
16 Spectral Methods for Dimensionality Reduction -
17 Modifying Distances -
18 Large-Scale Algorithms -
19 Semi-Supervised Protein Classification Using Cluster Kernels -
20 Prediction of Protein Function from Networks -
25 Analysis of Benchmarks -
22 An Augmented PAC Model for Semi-Supervised Learning -
23 Metric-Based Approaches for Semi-Supervised Regression and Classification -
24 Transductive Inference and Semi-Supervised Learning -
25 A Discussion of Semi-Supervised Learning and Transduction - References
- Notation and Symbols
- Contributors
- Index
Gaussian Processes and the Null-Category Noise Model
Gaussian Processes and the Null-Category Noise Model
- Chapter:
- (p.136) (p.137) 8 Gaussian Processes and the Null-Category Noise Model
- Source:
- Semi-Supervised Learning
- Author(s):
Lawrence Neil D.
Jordan Michael I.
- Publisher:
- The MIT Press
This chapter presents an augmentation of the standard probabilistic classification model which incorporates a null-category. Given a suitable probabilistic model for the model category, the chapter obtains a probabilistic counterpart of the margin. By combining this noise model with a Gaussian process classifier (GPC), it obtains a classification methodology that is simultaneously discriminative, semi-supervised, and Bayesian. The approach incorporates the cluster assumption without explicitly modeling the data density and without requiring specialized kernels. GPCs aim to predict the posterior probability of the class label yi given a covariate vector xi. Under the standard assumptions generally invoked by GPC practitioners, this posterior probability is unaffected by unlabeled data points, providing no role for unlabeled data.
Keywords: probabilistic classification model, null-category, Gaussian process classifier, GPC, classification methodology, cluster assumption, unlabeled data
MIT Press Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.
Please, subscribe or login to access full text content.
If you think you should have access to this title, please contact your librarian.
To troubleshoot, please check our FAQs, and if you can't find the answer there, please contact us.
- Title Pages
- Series Foreword
- Preface
-
1 Introduction to Semi-Supervised Learning -
1 A Taxonomy for Semi-Supervised Learning Methods -
3 Semi-Supervised Text Classification Using EM -
4 Risks of Semi-Supervised Learning: How Unlabeled Data Can Degrade Performance of Generative Classifiers -
5 Probabilistic Semi-Supervised Clustering with Constraints -
6 Transductive Support Vector Machines -
7 Semi-Supervised Learning Using Semi-Definite Programming -
8 Gaussian Processes and the Null-Category Noise Model -
9 Entropy Regularization -
10 Data-Dependent Regularization -
11 Label Propagation and Quadratic Criterion -
12 The Geometric Basis of Semi-Supervised Learning -
13 Discrete Regularization -
14 Semi-Supervised Learning with Conditional Harmonic Mixing -
15 Graph Kernels by Spectral Transforms -
16 Spectral Methods for Dimensionality Reduction -
17 Modifying Distances -
18 Large-Scale Algorithms -
19 Semi-Supervised Protein Classification Using Cluster Kernels -
20 Prediction of Protein Function from Networks -
25 Analysis of Benchmarks -
22 An Augmented PAC Model for Semi-Supervised Learning -
23 Metric-Based Approaches for Semi-Supervised Regression and Classification -
24 Transductive Inference and Semi-Supervised Learning -
25 A Discussion of Semi-Supervised Learning and Transduction - References
- Notation and Symbols
- Contributors
- Index
