Lectures are an essential part of our course. Here you can get lecture notes and course materials. Lectures and labs are typically scheduled on Thursday mornings between 9:30 and 12:30 and are held in the Institute of Information Theory and Automation (UTIA), room 25. If you have any questions please contact

## Exams

Exam dates: 13.1. and 20.1.

Place&time: UTIA, room 25, 9:30am

## Lectures schedule

**Lecture 1** – Introduction to Machine Learning 1/3 – 30.9.2021

Introduction to USU and SU2, what is AI, ML, handcrafted features versus learned features, supervised versus unsupervised learning, AI as an optimization problem

**Lecture 2** – Introduction to Machine Learning 2/3 – 7.10.2021

Bayesian classifier, K-NN classifier, SVM, k-means clustering, PCA

**Lecture 3** – Introduction to Machine Learning 3/3, Introduction to Deep Learning – 14.10.2021

**Lecture 4/Lab** – Decision trees – 4.11.2021

Random forest, AdaBoost, XgBoost

The second half of the lecture will be practical with hands-on examples.

**Lecture 5** – Neural Networks – 11.11.2021

NN theory, output units, hidden units, activation functions

**Lecture 6** – Optimization, CNN – 25.11.2021

stochastic optimization (SGD, ADAM,…), CNN building blocks

**Lecture 7** – Advanced Topics – 9.12.2021

regularization, examples of CNN architecture, GAN, VAE, RNN, Transformer

## Handouts

Lectures 1-3: Introduction to Machine Learning

Lecture 3b: Introduction to Deep Learning

Lecture 5: Theory and Basic Building Blocks

Lecture 6: Optimization and CNN architecture

Lecture 7: Advanced Topics