Lecture: Optimization Methods for Machine Learning
The lecture (LSF) will be taught in English and addresses Master and PhD students in Mathematics or related fields. The lecture is expected to be more interactive than other lectures.
Different Room on November 26, 2018
Because of a workshop that takes place in room G03-214, we are going to move on Monday, November 26, 13h15 to room G05-307.
- Lecture with 4+2 SWS and 9 ECTS-Credits
- Place and time: Mo 13:15 - 14:45, G03-214;
Di 15:15 - 16:45, G03-214
It will survey optimization problems in and methods for machine learning. Updates on this page will follow.
A preliminary table of contents is the following.
- 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
- Methods for (Non-Smooth) Regularized Models
- Ethical and Philosophical Aspects of Artifical Intelligence
Practical exercises will complement the lecture and focus on KERAS and Python scikit-learn.
Introduction to Optimization. The lecture Nonlinear Optimization is recommended, but not absolutely necessary.
Exercises and Downloads
On this password-protected page
Studienfächer / Studienrichtungen
- WPF MA;D ab 6 (Modul 12, 13, 14)
- WPF MA;M 1-3 (Modul M3D)
Feel free to send me an email with general questions:
Last Modification: 2018-10-23 - Contact Person: Sebastian Sager - Impressum