Understanding Machine Learning:  From Theory to Algorithms/ 
Shai Shalev-Shwartz and Shai Ben-David 
 - New Delhi :   Cambridge University  Press,  2014 
 - 397p;,  xvi,  24cm. 
<br/><br/> Preface.<br/>CONTENS<br/>1. Introduction.<br/>Part I Foundations.<br/>2. A Gentle Start.<br/>3. A Formal Learning Model.<br/>4. Learning Via Uniform Convergence.<br/>5. The Bias-Complexity Trade-Off.<br/>6. The CV Dimension.<br/>7. Nonuniform Learnability. <br/>8. The Runtime of Learning.<br/>Part 2 From Theory to algorithms.<br/>9. Linear Predictors.<br/>10. Boosting.<br/>11. Model Selection and Validation.<br/>12. Convex Learning Problems.<br/>13. Regularization and Stability.<br/>14. Stochastic Gradient Descent.<br/>15. Support Vector Machines.<br/>16. Kernel methos.<br/>17. Multiclass, Ranking, and Complex Prediction Problems.<br/>18. Decision Trees.<br/>19. Nearest Neighbour.<br/>20. Neural Networks.<br/>Part III Additional Learning Model.<br/>21. Online Learning.<br/>22. Clustering.<br/>23. Dimensionality Reduction.<br/>24. Generative Models.<br/>25. Feature Selection and Generation.<br/>Part IV Advanced Theory.<br/>26. Rademacher Complexities.<br/>27. Covering Numbers.<br/>28. Proof of the Fundamentals.<br/>29. Multiclass Learnability.<br/>30. Compression Bounds.<br/>31. PAC-Bayes.<br/>Appendix A Technical Lemmas.<br/>Appendix B Measure Concentration.<br/>Appendix C Linear Algebra.<br/>Reference.<br/>Index.<br/> 
<br/><br/><label>ISBN: </label>9781107512825 
<br/><br/><label>Dewey Class. No.: </label>006.31  / SHW