Description
Book SynopsisMachine learning is one of the fastest growing areas of computer science, with far-reaching applications. This book explains the principles behind the automated learning approach and the considerations underlying its usage. The authors explain the 'hows' and 'whys' of machine-learning algorithms, making the field accessible to both students and practitioners.
Trade Review'This elegant book covers both rigorous theory and practical methods of machine learning. This makes it a rather unique resource, ideal for all those who want to understand how to find structure in data.' Bernhard Schölkopf, Max Planck Institute for Intelligent Systems, Germany
'This is a timely text on the mathematical foundations of machine learning, providing a treatment that is both deep and broad, not only rigorous but also with intuition and insight. It presents a wide range of classic, fundamental algorithmic and analysis techniques as well as cutting-edge research directions. This is a great book for anyone interested in the mathematical and computational underpinnings of this important and fascinating field.' Avrim Blum, Carnegie Mellon University
'This text gives a clear and broadly accessible view of the most important ideas in the area of full information decision problems. Written by two key contributors to the theoretical foundations in this area, it covers the range from theoretical foundations to algorithms, at a level appropriate for an advanced undergraduate course.' Peter L. Bartlett, University of California, Berkeley
Table of Contents1. Introduction; Part I. Foundations: 2. A gentle start; 3. A formal learning model; 4. Learning via uniform convergence; 5. The bias-complexity trade-off; 6. The VC-dimension; 7. Non-uniform learnability; 8. The runtime of learning; Part II. From Theory to Algorithms: 9. Linear predictors; 10. Boosting; 11. Model selection and validation; 12. Convex learning problems; 13. Regularization and stability; 14. Stochastic gradient descent; 15. Support vector machines; 16. Kernel methods; 17. Multiclass, ranking, and complex prediction problems; 18. Decision trees; 19. Nearest neighbor; 20. Neural networks; Part III. Additional Learning Models: 21. Online learning; 22. Clustering; 23. Dimensionality reduction; 24. Generative models; 25. Feature selection and generation; Part IV. Advanced Theory: 26. Rademacher complexities; 27. Covering numbers; 28. Proof of the fundamental theorem of learning theory; 29. Multiclass learnability; 30. Compression bounds; 31. PAC-Bayes; Appendix A. Technical lemmas; Appendix B. Measure concentration; Appendix C. Linear algebra.
