Bibliography .pdf
Preface .pdf
1 - Introduction .pdf
2 - The Pattern Classification Problem .pdf
3 - The Growth Function and VC-Dimension .pdf
4 - General Upper Bounds on Sample Complexity .pdf
5 - General Lower Bounds on Sample Complexity .pdf
6 - The VC-Dimension of Linear Threshold Networks .pdf
7 - Bounding the VC-Dimension using Geometric Techniques .pdf
8 - Vapnik-Chervonenkis Dimension Bounds for Neural Networks .pdf
9 - Classification with Real-Valued Functions .pdf
10 - Covering Numbers and Uniform Convergence .pdf
11 - The Pseudo-Dimension and Fat-Shattering Dimension .pdf
12 - Bounding Covering Numbers with Dimensions .pdf
13 - The Sample Complexity of Classification Learning .pdf
14 - The Dimensions of Neural Networks.pdf
15 - Model Selection .pdf
16 - Learning Classes of Real Functions .pdf
17 - Uniform Convergence Results for Real Function Classes .pdf
18 - Bounding Covering Numbers .pdf
19 - Sample Complexity of Learning Real Function Classes .pdf
20 - Convex Classes .pdf
21 - Other Learning Problems .pdf
22 - Efficient Learning .pdf
23 - Learning as Optimization .pdf
24 - The Boolean Perceptron .pdf
25 - Hardness Results for Feed-Forward Networks .pdf
26 - Constructive Learning Algorithms for Two-Layer Networks.pdf
Appendix 1 - Useful Results .pdf
notes.txt