# Foundations of Machine Learning

Three weeks, 15 days, a lecture and exercises every day. The three-week course takes place from 9:00-17:00 at the University IT and Data Center (Hochschulrechenzentrum HRZ). The course structure is 90 minutes of lecture 90 min exercises, followed by 4 hrs of programming under guidance from the tutors.

Prerequisites:

Programming in Python. If you are not yet familiar with python, please consult https://docs.python.org/3/tutorial/ before the first session.

Course contents:

Week I, Basics

Day 1: Introduction

- What is machine learning, and what can it do for us?

Day 2: Optimization

- The derivative, gradients, optimization via gradient descent.

Day 3: Linear Algebra:

- Matrix multiplication, singular value decomposition, Linear Regression.

Day 4: Statistics - Probability Theory I

- random variable, mean and variance, conditional probability.

Day 5: Statistics - Probability Theory II

- common probability distributions, correlation and auto-correlation.

Week 2, Foundations of machine learning

Day 1: Machine learning basics

- Overfitting and underfitting, classification, regression, k-nearest neighbours.

Day 2: Support vector machines

- Linear separable, non-linear separable, kernel trick.

Day 3: Decision trees and random forests:

- Decision trees, random forests, bias and variance problem, bagging.

Day 4: Clustering and density estimation

- K-means clustering, Gaussian mixture models, expectation-maximization.

Day 5: Principal component analysis (PCA)

- PCA for dimensionality reduction, PCA for compression and other applications.

Week 3, Deep Learning

Day 11: Fully connected networks:

- The MNIST-data set, artificial neurons, forward and backward pass.

Day 12: Convolutional neural networks:

- The convolution operation and convolutional neural networks.

Day 13: Optimization for deep neural networks:

- gradient descent with momentum, Adam, early stopping, regularization.

Day 14: Interpretability:

- visualization of linear classifiers, saliency maps, integrated gradients

Day 15: Sequence models:

- Long-Short-Term-Memory, Gated recurrent units, text-based language models.

See you during the course,

Your lecturers, Elena and Moritz.

We thank the state of North Rhine-Westphalia and the Federal Ministry of Education and Research for supporting this project.

### Next Course

Date

**March 13 until March 31**

09:00 - 17:00

Location

- PC-room 0.012 at the HRZ, Wegelerstr. 6.

**Contact**

**moritz.wolter at uni-bonn.de,****trunz at cs.uni-bonn.de**