Lectures


header.tex

Introduction [ps] [pdf]
Maximal margin classification [ps] [pdf]
Introduction to kernels [ps] [pdf]
Ridge regression and kernels [ps] [pdf]
Properties of kernels [ps] [pdf]
Soft-margin SVM, sparseness [ps] [pdf]
Regression, the SVD and PCA [ps] [pdf]
Kernel PCA and kernel CCA
Incomplete Cholesky decomposition [ps] [pdf]
ANOVA kernels and diffusion kernels [ps] [pdf]
String kernels and marginalized kernels [ps] [pdf]
Fisher kernels and semidefinite programming [ps] [pdf]
Multiple kernels and RKHS introduction [ps] [pdf]
Reproducing kernel Hilbert spaces I [ps] [pdf]
Reproducing kernel Hilbert spaces II [ps] [pdf]
The Representer Theorem [ps] [pdf]
Gaussian processes I [ps] [pdf]
Gaussian processes II [ps] [pdf]
Gaussian processes and reproducing kernels [ps] [pdf]
Spectral clustering [ps] [pdf]
Spectral clustering, introduction to Bayesian methods [ps] [pdf]
Conjugacy and exponential family [ps] [pdf]
Importance sampling and MCMC
Properties of Dirichlet distribution [ps] [pdf]
Dirichlet processes I [ps] [pdf]
Dirichlet processes II [ps] [pdf]
Dirichlet process mixtures I [ps] [pdf]
Dirichlet process mixtures II [ps] [pdf]
Probabilistic formulation of prediction problems [ps]
Risk bounds, concentration inequalities [ps]
Glivenko-Cantelli classes and Rademacher averages [ps]
Growth function and VC-dimension [ps]
Applications of Rademacher averages in large margin classification [ps]
Growth function estimates for parameterized binary classes [ps]
Covering numbers and metric entropy [ps]
Chaining, Dudley's entropy integral [ps]
Covering numbers of VC classes [ps]
Bernstein's inequality, and generalizations [ps]