ECE 6254, Spring 2016
Statistical Learning and Signal Processing
Slides 1, Introduction
Slides 2, Notes 2, The Bayes classifier
Slides 3, Notes 3, A first look at the theory of learning
Slides 4, k-nearest neighbor classification
Slides 5, plugin methods: LDA and logistic regression
Notes on the convergence of gradient descent and Newton’s method
Slides 6, linear classifiers: the perceptron and maximum margin
Slides 8, overview of constrained optimization
Slides 9, Notes 9, support vector machines
Slides 10, Notes 10, A second look at the theory of learning
Slides 11, Notes 11, regression and regularization
Slides 12, bias vs. variance
Slides 13, validation and model selection
Slides 14, neural nets
Slides 15, feature selection
Slides 16, clustering, K-means, GMMs, EM algorithm
Slides 17, Notes 17, principal components analysis (PCA)
Slides 18, nonlinear dimensionality reduction (MDS, ISOMAP, LLE)
Notes 19, spectral clustering
Notes 20, structured matrix factorization