EPFL course EE613 - Machine Learning for Engineers
EPFL webpage for the complete EE613 course
EPFL Moodle with labs exercises
HIDDEN MARKOV MODELS
Content:- Markov models
- Hidden Markov model (HMM)
- Forward-backward algorithm
- Expectation-maximization (EM)
- Viterbi decoding (dynamic programming)
- Hidden semi-Markov model (HSMM)
- HMM with dynamic features (Trajectory-HMM)
- Lecture slides: EE613-hiddenMarkovModels.pdf
LINEAR REGRESSION
Content:- Least squares
- Singular value decomposition (SVD)
- Nullspace projection (kernels in least squares)
- Ridge regression (Tikhonov regularization)
- Weighted least squares
- Iteratively reweighted least squares (IRLS)
- Recursive least squares
- Logistic regression
- Lecture slides: EE613-linearRegression.pdf
NONLINEAR REGRESSION
Content:- Properties of multivariate Gaussian distributions:
- Product of Gaussians
- Linear transformation and combination
- Conditional distribution
- Gaussian estimate of a mixture of Gaussians
- Locally weighted regression (LWR)
- Gaussian mixture regression (GMR)
- Gaussian process regression (GPR)
- Lecture slides: EE613-nonlinearRegression.pdf
TENSOR FACTORIZATION
Content:- Tensor-variate data and tensor networks
- Multilinear algebra
- Hadamard, Kronecker, Khatri-Rao products
- Canonical polyadic (CP) decomposition
- Tucker decomposition
- Tensor train decomposition
- Lecture slides: EE613-tensorFactorization.pdf