Learning Outcomes
Participants should learn basic concepts, their theoretical foundation, and the most common algorithms used in machine learning and artificial intelligence. After completing the module, participants should understand strengths and limitations of the different paradigms, should be able to correctly and successfully apply methods and algorithms to real world problems, should be aware of performance criteria, and should be able to critically evaluate results obtained with those methods. More specifically, participants should be able to demonstrate:
1) Understanding regarding basic concepts of neural information processing
2) Knowledge of unsupervised machine learning methods
3) Application to problems of statistical modeling, explorative data analysis, and visualisation
Content
1) Principal Component Analysis, Kernel-PCA
2) Independent Component Analysis (Infomax, FastICA, Second Order Blind Source Separation)
3) Stochastic Optimization
4) Clustering, Embedding, and Visualisation (Central and Pairwise Clustering, Self-Organizing Maps, Locally Linear Embedding)
5) Density Estimation, Mixture Models, Expectation-Maximization Algorithm, Hidden Markov Model
6) Estimation Theory, Maximum Likelihood Estimation, Bayesian Model Comparison
Description of Teaching and Learning Methods
Lecture: Teaching in front of the class to convey the content.
Exercise: Discussion of exercises which cover the mathematical derivation and analysis of neuronal methods as well as the implementation and practical usage of these methods.
Registration Procedures
The registration for the written exam is possible at the end of the term through the electronic system of TU Berlin (as of 2017: QISPOS) or alternatively in written form via the examination office. The written exam is held in English. Both potential re-examinations are oral exams. Other than that, the examination procedure is regulated by the General Examination Regulation of the TU Berlin (AllgStuPO) and by the Examination Regulation of the Master Program Computational Neuroscience.
Further information regarding registration and course material are available via the respectively current ISIS course.