Inhalt der Veranstaltung

The seminar deals with the theory of machine learning from a (mathematically) rigorous statistical perspective. The so-called PAC (probably almost correct) learning framework focusses on the question how well a machine learning algorithm which was trained on random independent data can make predictions on new instances which are generated from the same but unknown probability distribution.

After explaining the statistical learning framework, the seminar will discuss uniform convergence results and the VC dimension. It will also discuss theoretical aspects of different machine learning models, such as convex learning, support vector machines, boosting, online learning and stochastic gradient descent. It will cover regularisation, model selection and dimensionality reduction. Rademacher complexities will be included.

We will have a first online meeting for explaining the goal of the seminar and the registration process:

Diese Veranstaltung ist Bestandteil des gleichnamigen Moduls mit 3 LP (2 SWS).

ISIS webpage : https://isis.tu-berlin.de/course/view.php?id=22421 (id = 22421) 

Content of the course The projects should allow students to develop an understanding of recent (mostly probabilistic) ideas and techniques in the research areas of Machine Learning and Artificial Intelligence. Projects will be based mainly on original literature (research papers or textbook contributions, usually written in English) and might come from areas such as reinforcement learning, active learning, probabilistic ICA and Bayesian learning of dynamical systems. Assessment of the projects will be based on a written project report and a seminar presentation (in German or English).

We will have a first online meeting for explaining the goal of the seminar and the registration process:

This course is part of module PJ Stat. Methoden  (9LP)

 ISIS Webpage : https://isis.tu-berlin.de/course/view.php?id=22420 (id = 22420)

Content of the course The seminar gives a practical overview of application of algorithms in Artificial Intelligence. It is meant to be an additional course to the lecture and exercise Künstliche Intelligenz: Grundlagen und Anwendungen.

Lecturer: Dr. Andreas Ruttor,   LV 3435 L722 seminar in Artificial Intelligence. It is part of module 3945, KI: Grundlagen, Anwendungen und Seminar - 3LP -. This course is avaible online via ISIS. Please enroll there for further information.