Course organized by TUT, see TUT study guide for up-to-date information.
Learning outcomes
Students understand principles of selected pattern recognition and machine learning approaches for interpreting signals. Student can apply the methods to real problems.
Contents
- Historical perspective to signal interpretation using pattern recognition and machine learning (concept learning, expert systems etc.) Practical application examples. - Decision tree learning and random forests. - Bayesian decision making and learning. - Probability, decision and information theories in machine learning and pattern recognition. - Probability distributions. Mixture models and EM. - Linear models for regression and classification. - Algorithm-independent machine learning. Evaluating hypothesis. No free lunch theorem, Occam's razor and cross-validation. High-dimensional problems. Feature selection.