##### News

The lecture (LSF) will be taught in English and addresses Master and PhD students in Mathematics or related fields. We will discuss the format in our first meeting. Slides of the lectures and videos of lectures are available.

##### Information

- Lecture with 4+2 SWS and 9 ECTS-Credits
- Lecturer practical exercises

##### Content

It will survey optimization problems in and methods for machine learning. Table of contents:

- Introduction to Machine Learning
- Machine Learning Case Studies: text classification and perceptual tasks
- Problem Definitions and Methods Overview
- Efficient Calculation of Derivatives
- Problem reformulations
- Stochastic Gradient Methods
- Noise Reduction Methods
- Second-Order Methods
- Other Popular Methods
- Ethical, Philosophical, and Economical Aspects of Artifical Intelligence

Practical exercises will complement the lecture and focus on *KERAS* and *Python scikit-learn*.

##### Requirements

Mathematical basics (Analysis and Linear Algebra) and programming skills. *Introduction to Optimization*. The lecture *Nonlinear Optimization* is highly recommended, but not absolutely necessary.

##### Module description

The lecture is a master lecture in the mathematics curriculum and described in the module handbook (currently page 31) as a*Wahlpflicht*module:

- WPF MA (Module 12, 13, 14)
- WPF MA;M 1-3 (Module M3D)

A translation of the module description:

*Goals and competences:*The students acquire competences with respect to modeling and algorithmically solving optimization problems that are at the basis of modern machine learning techniques. A rigorous mathematical analysis of convergence theory and implementation aspects of different algorithms is the guiding theme of the lecture. In the exercises the students learn how to implement algorithms efficiently on a computer and to apply them to concrete problem instances.*Content:*An introduction to mathematically formulating machine learning problems in a generalized way, calculating derivatives, stochastic and deterministic derivative-based algorithms, convergence theory. See above for a table of contents.

The lecture is also open to other master and PhD students of OVGU. In particular, there is an agreement that **ORBA** students may choose the lecture as a *Wahlpflicht* (with 10 CP to motivate the independent study of mathematical foundations necessary to follow the lecture). However, please note that the lecture is addressed to mathematical master students and assumes a good understanding of mathematical basics, especially in the second part of the lecture. If you are mainly interested in *applying* machine learning and not so much in *analyzing* the training process, other lectures might be better suited for you. Note that the lecture *Concepts and Algorithms of Optimization* is not sufficient as a requirement, you will have to invest more time to acquire additional mathematical knowledge.

##### Material: mathematical background

- Roadmap of Mathematics for Deep Learning, a collection of necessary mathematical background with links to online ressources in Mathematics

##### Material: machine learning

- Jason Mayes Machine Learning 101
- 7 steps of Machine Learning (Google Cloud)
- Neural Networks
- Neural networks and backpropagation
- Convolutional Networks
- Corresponding text
- Convolution arithmetics with animations
- Generative Adversarial Networks
- Overview of Neural Networks
- Datasets for Machine Learning
- Free ML courses from Amazon ML University
- Neural Networks by 3Blue1Brown
- Approximation Properties of Neural Networks

##### Material: optimization and machine learning

- Optimization Methods for Large-Scale Machine Learning survey paper by Bottou, Curtis, Nocedal
- Home page of Julien Mairal with many related talks
- Artificial Intelligence Summer School, July 2018, Grenoble
- The mathematics behind Deep Learning
- The Connection Between Applied Mathematics and Deep Learning

##### Material: AI and the future of mankind

- Spiegel Online Article giving reference to the study
*The Future of Jobs* - Zeit Online Podcast with Richard Socher (in German)
- Zeit Online Podcast with Yuval Harari

##### Material: hands on

- Python Data Science Handbook
- Harvard Data Science Course
- Scikit Learn
- Scikit Learn Test Datasets
- Scikit Learn Algorithm Cheat Sheet
- Facebook research projects
- Google AI resources

##### Questions?

Feel free to send me an email with general questions: