Dates & Overview
Kickoff: April, 16th of April, 11:00 am
Block: Friday, 25th of June, 1:00 pm-4:00 pm
Key: Seminar_DUL
Target groups: Master Statistics, Master Data Science
Course Description
Deep learning algorithms have made outstanding results in many domains such as computer vision (CV), natural language processing (NLP), recommendation systems, and medical image analysis. However, the outcome of current methods depends on a huge amount of training labeled data, and in many real-world problems such as medical image analysis and autonomous driving, it is not possible to create such an amount of training data. Learning from unlabeled data can reduce the deployment cost/time of deep learning algorithms where it requires annotations from experts such as medical professionals and doctors.
In this course, we will learn about the theory of deep unsupervised learning and will review some state-of-the-art methods. We will offer different topics with different applications (i.e. NLP, CV) for a variety of tasks (i.e. clustering, representation learning, density modeling, etc). As part of the seminar, you will also apply one of the frameworks to a given real-world problem. This means every participant will be asked to prepare an oral presentation about a current technique and to write up a reproducible case study of actual data analysis in an unsupervised DL framework, in addition to peer-reviewing the (theoretical and practical) work of a colleague.
Recommended prerequisites: Deep learning; Python, PyTorch, TensorFlow, We would also hold the seminar in English and also allow students from other courses (especially DS students)
Preliminary meeting:
April 16th, 11:00 - 12:30
Virtual Room:
Seminar: Blocked towards the end of the semester (1-2 units)
- Trainer/in: Mina Rezaei