Preface
Overview
Audience
Organization
Contents
Acronyms
1 Introduction
1.1 Machine Learning (ML) System
1.2 Main Steps in an ML System
1.2.1 Data Collection/Acquisition
1.2.2 Feature Engineering and Representation
1.2.3 Model Selection
1.2.4 Model Estimation
1.2.5 Model Validation
1.2.6 Model Explanation
1.3 Data Sets Used
1.4 Summary
References
2 Representation
2.1 Introduction
2.2 Representation in Problem Solving
2.3 Representation of Data Items
2.4 Representation of Classes
2.5 Representation of Clusters
2.6 Summary
References
3 Nearest Neighbor Algorithms
3.1 Introduction
3.2 Nearest Neighbors in High-Dimensional Spaces
3.3 Fractional Norms
3.4 Locality Sensitive Hashing (LSH) and Applications
3.5 Summary
References
4 Representation Using Linear Combinations
4.1 Introduction
4.2 Feature Selection
4.3 Principal Component Analysis
4.4 Random Projections
4.5 Non-negative Matrix Factorization
4.6 Summary
References
5 Non-linear Schemes for Representation
5.1 Introduction
5.2 Optimization Schemes for Representation
5.3 Visualization
5.4 Autoencoders for Representation
5.5 Experimental Results: ORL Data Set
5.6 Experimental Results: MNIST Data Set
5.7 Summary
References
6 Conclusions
References
Index