About This Course
The course is a combination of applied and theoretical aspects of deep learning. In addition to discussing recent state-of-the-art models in both supervised and unsupervised learning, we delve into the details of various network architectures for processing texts and images. Special emphasis will be put on learning how to work with deep learning libraries, particularly Tensorflow 2.0.
In this course you will learn the foundations of deep learning, understand various neural network architectures, and practice developing machine learning projects from scratch.
Full website: http://teias-courses.github.io/dl99
Learning Objectives
The course is a combination of applied and theoretical aspects of deep learning. In addition to discussing recent state-of-the-art models in both supervised and unsupervised learning, we delve into the details of various network architectures for processing texts and images. Special emphasis will be put on learning how to work with deep learning libraries, particularly Tensorflow 2.0.
Course weekly plan
Flipped style classroom:
- Lecture (Sundays),
- TA Session (Tuesdays),
- Project Mentorship (Wednesdays)
Announcements
(No information at the moment, a place holder for future announcements.)
Reading Material
Mandatory Reading
- Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning, MIT Press.
- The Deep Learning Specialization on Coursera
Recommended Reading
- Christofer Bishop, Pattern Recognition and Machine Learning, Springer.
Slides and Handouts

(No information at the moment, a place holder for future material)
Assessment and Feedback
(will links to a separate page)
Marking Criteria
- 5% – Attendance
- 15% – Quiz, midterm and final exam
- 40% – Homeworks and programming assignments
- 40% – Final project