TU Berlin

Kontinuumsmechanik und MaterialtheorieIntroduction to Machine Learning (SoSe 19)

Inhalt des Dokuments

zur Navigation

Introduction to Machine Learning

Educational objectives: 

Linear Regression, Logistic Regression, Regularization, Full-connected Neural Networks, Backpropagation algorithm, Convolutional Neural Networks, the Bayes Theorem, application to selected problems.

  

Target Audience:

Machine learning is the science of getting computers to act without being explicitly programmed. It rapidly evolving in the modern world and is needed for many problems in engineering, business, medicine etc. For example, in the past decade machine learning has given us self-driving cars, practical speech recognition, the victory of a computer over one of the world's strongest players of the game Go and helped us in the problem of particle identification in LHC experiments.
This course addresses students majoring in computer science, engineering sciences, physics, mechanical engineering, and similar university courses. Basic knowledge of linear algebra and confident programming is helpful.

 

Dates:

The course is given as a block seminar in June and July by Dr. Murachev in a four-week period. In the first lecture (Wednesday, 19.06., 14:00--16:00, room: MS 307), the procedure of the course and the exam regulations are detailed. There are two lectures and two consultation hours per week until Friday, 12.07. Please see the module descriptor for further information on the schedule.

 

Module descriptor:

See this link.

 

 

Navigation

Direktzugang

Schnellnavigation zur Seite über Nummerneingabe