Mathematical Foundations for Machine Learning
Date:
7.10.19 - 11.10.19
Room:
EW 203
Test:
25.10.19 (room and time TBA)
Lecturer:
Jacob Kauffmann (j.kauffmann@tu-berlin.de)
Informations
The goal of this course is to freshen and deepen the mathematical foundations from the computer science program that are necessary for the lectures Cognitive Algorithms and Machine Learning.
Topics of the course come from analysis (differentiation), linear algebra (vector spaces, dot products, orthogonal vectors, matrices as linear maps, determinants, eigenvalues and eigenvectors) and probability theory (multivariate probability distributions, calculations with expectation values and variances).
More information can be found on ISIS.
Structure
Attendance is not mandatory. The structure is roughly given below:
10:00 – 11:30 am |
Introductory lecture |
11:30 - 3:00 pm |
Work on exercise sheets |
3:00 - 4:00 pm |
Review of exercise sheets |
4:00 – 5:00 pm |
Work on homework sheets |
Preliminary structure:
- 07.10. - Linear Algebra I: Groups, Fields and Euclidean Vector Spaces
- 08.10. - Linear algebra II: Linear Transformations, Matrices and Determinants
09.10. - No classes
- 10.10. - Analysis: Differentiation and ML Examples
- 11.10. - Probability Theory
Credits
The course is compulsory for the modules Machine Learning 1 (M.Sc. Informatik) and Cognitive Algorithms (B.Sc. Informatik).
Registration is not necessary, students of all fields an universities are invited. Basis for the grading (2 SWS / 2 LP) is a test (90 minutes). Prerequisite for the participation in the test is the achievement of at least half of all possible points in the homework, the results in the exercises are not included in the grade.