Frequentist Machine Learning
Machine learning from a primarily Bayesian perspective. Conjugate priors. Bayesian linear regression, model evidence, linear classification using generative models, logistic regression and the Laplace approximation. Kernel methods and Gaussian process regression. Mixture models, expectation maximization, hidden Markov models, sampling methods and Markov chain Monte Carlo.
Prerequisites: MA 223, MA 224; either ECE 211, ChE 352 or ME 251
Credits: 3.00
Course Code: ECE 475