Introduction to modern machine learning, in particular probabilistic models and deep learning, as well as an overview of its applications at ISTA.
Syllabus:
- Probabilistic Models
- Deep Learning
- Optimization
- Unsupervised Learning
- Applications at ISTA
Target group: anyone who plans to develop or use Machine Learning / Artificial Intelligence techniques in their PhD
Prerequisites: Linear Algebra, Calculus, Probability, Scientific Programming in Python
Evaluation: participation, regular assignments, exam (might be waived)
Teaching format: lectures, homework, potentially project work
ECTS: 6 Year: 2022
Track segment(s):
Elective
Teacher(s):
Christoph Lampert Dan Alistarh Marco Mondelli Bingqing Cheng Matthew Robinson
Teaching assistant(s):
Elias Frantar Jonathan Scott
If you want to enroll to this course, please click: REGISTER
- Teacher: Dan-Adrian ALISTARH
- Teacher: Bingqing Cheng
- Teacher: Christoph Lampert
- Teacher: Marco Mondelli
- Teacher: Matthew Robinson
- Teaching Assistant: Elias Frantar
- Teaching Assistant: Jonathan Scott