Mathematical Foundations for Machine Learning
Lecture period:
June 5th - July 14th
Contact:
Thomas Schnake (t.schnake@tu-berlin.de)
ISIS Course:
Information
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).
Structure
The weekly structure between the 5.6. and 7.7. is given below:
Tue 10:15 - 11:45 am
Lecture
Thu 10:15 - 11:45 am
Exercise
Exercise sheets will be collected in the lecture.
Preliminary structure:
- Week 1 - Linear Algebra I: Groups, Fields and Euclidean Vector Spaces
- Week 2 - Linear algebra II: Linear Transformations, Matrices and Determinants
- Week 3 - Analysis: Differentiation and ML Examples
- Week 4 - Probability Theory
- Week 5 - Selected Subject - Mathematics in Machine Learning Today
- Week 6 - Online Test
Credits
The course is part of the module Machine Learning 1-X (M.Sc. Informatik) and optional for Cognitive Algorithms (B.Sc. Informatik).
Registration is desired but not necessary to attend the course. Students of all fields and universities are invited.