Master
2023/2024
Research Seminar "Deep Learning"
Type:
Compulsory course (Master of Data Science)
Area of studies:
Applied Mathematics and Informatics
Delivered by:
Big Data and Information Retrieval School
Where:
Faculty of Computer Science
When:
2 year, 2 module
Mode of studies:
offline
Open to:
students of one campus
Instructors:
Yury Sanochkin
Master’s programme:
Магистр по наукам о данных (заочная)
Language:
English
ECTS credits:
3
Contact hours:
10
Course Syllabus
Abstract
In this course we discuss a variety of Deep Learning scientific papers and practice understanding, presenting and reviewing them. We cover papers in different areas of DL such as Natural Language Processing and Computer vision and move from basic to more complicated ideas and more recent developments. The course programme is different for two “tracks”: the deep learning one (for students who have taken the introduction to deep learning course) and the math track. The deep learning track covers more complex papers which require the understanding of basic neural network architectures and traning process. The math track focuses on the basic consepts and tries to introduce them on examples of fundamental papers and overviewing blog posts.