9.520-A | Spring 2001 | Graduate

Networks for Learning: Regression and Classification


1 The Course at a Glance
2 The Learning Problem in Perspective
3 Regularized Solutions
4 Reproducing Kernel Hilbert Spaces
5 Classic Approximation Schemes
6 Nonparametric Techniques and Regularization Theory
7 Ridge Approximation Techniques
8 Regularization Networks and Beyond
9 Applications to Finance
10 Introduction to Statistical Learning Theory
11 Consistency of the Empirical Risk Minimization Principle
12 VC-Dimension and VC-bounds
13 VC Theory for Regression and Structural Risk Minimization
14 Support Vector Machines for Classification
15 Project Discussion
16 Support Vector Machines for Regression
17 Current Topics of Research I: Kernel Engineering
18 Applications to Computer Vision and Computer Graphics
19 Neuroscience I
20 Neuroscience II
21 Current Topics of Research II: Approximation Error and Approximation Theory
22 Current Topics of Research III: Theory and Implementation of Support Vector Machines
23 Current Topics of Research IV: Feature Selection with Support Vector Machines and Bioinformatics Applications
24 Current Topics of Research V: Bagging and Boosting
25 Selected Topic: Wavelets and Frames
26 Project Presentation

Course Info

As Taught In
Spring 2001
Learning Resource Types
Problem Sets
Written Assignments