Generic and Transferable Skills (GTS courses)
PhD courses given by the department
Pattern Classification and Machine Learning
- Course code: FSSY070
- Course higher education credits: 8.0
- Department: ELECTRICAL ENGINEERING
- Graduate school: Signals and Systems
- Course is normally given: The course will be given in the spring 2018.
- Language: The course will be given in English
1. Introduction: outline, "road map" for classification methods
Signal characterization, discriminative features, feature normalization, examples.
2. Supervised learning methods
ML, Bayesian parameter estimation for pattern classification;
Statistical learning and boosting methods (Support Vector Machines and Adaboost);
Bayesian and belief networks;
GMMs and EM algorithm.
3. Unsupervised learning methods
ML parameter estimation for component densities from the mixture density;
Clustering methods (K-means, mean-shift);
Topic models and BoW (bag of words);
4. Automated learning of features
NNs and deep learning.
1. Richard O. Duda, Peter E. Hart, David G. Stork, Pattern classification, John Wiley & Sons, 2nd Ed.
2. Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer.
3. David Barber, Bayesian reasoning and machine learning, Cambridge university press, 2012.
4. Related state-of-the-art publications and tutorial materials
5. Matlab toolbox for PR.
Home exercises and Exam:
Solving several theoretical problems
Matlab programs on several selected topics and presentations
Written exam: assignment of problem solving and programming tasks.