COURSE INFORMATION PACKAGE · INF 609

Mathematics for Machine Learning

Elective · English
ECTS
8
Local Credit
3
Theory + Practice + Lab
3 + 0 + 0
Course Level
Doctoral Degree
Prerequisites
-
Semester
1
On this page
Content Weekly Contents
Course Instructor(s)
Marie Christine PEROUEME
mcperoueme@voila.fr

Content

Objective

Artificial learning algorithms are based on a serious mathematical basis in the background. This course aims to strengthen those mathematical foundations.

Course Content

Within the scope of this course, the mathematical foundations underlying artificial learning algorithms are examined.
In this course, students are introduced to courses they have previously taken at undergraduate level, such as linear algebra, calculus and probability, and their relationship with artificial learning algorithms is examined.

Course Learning Outcomes

Students who successfully complete this course;

1. Have the necessary mathematical infrastructure for artificial learning algorithms.

2. Gains the ability to establish and apply the relationship between artificial learning algorithms and mathematical foundations.

3. Gains the theoretical knowledge to design artificial learning algorithms from scratch.

4. Gains project development skills with Artificial Learning algorithms.

5. Can understand the mathematical foundations of cutting edge algorithm in fields.

Teaching and Learning Methods

In class

References

Mathematics for Machine Learning Companion webpage to the book "Mathematics for Machine Learning". Copyright 2020 by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong Published by Cambridge University Press.

Weekly Contents

Theory Topics
Week Weekly Contents
1 Introduction to Mathematics for Artificial Learning
2 Linear algebra
3 Analytic Geometry
4 Matrix Decomposition I
5 Matrix Decomposition II
6 SVM
7 Calculus II
8 Calculus II
9 Week Midterms Exam
10 Optimization I
11 Optimization II
12 Probability Distributions I
13 Probability Distributions II
14 Linear regression