This course provides a thorough understanding of the fundamental concepts and recent advances in deep learning. The main objective is to provide students practical and theoretical foundations to use and develop deep neural architectures to solve challenging tasks in an end-to-end manner. The course is taught by Erkut Erdem.
The course will use Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville as the textbook (draft available online and for free here).
Instruction style: During the semester, students are responsible for studying and keeping up with the course material outside of class time. These may involve reading particular book chapters, papers or blogs and watching some video lectures. After the first four lectures, each week a group of students will present a research paper related to the topics of the week.
Lectures: Wednesday at 13:40-16:30 (D6)
The course webpage will be updated regularly throughout the semester with lecture notes, presentations, assignments and important deadlines. All other course related communications will be carried out through ed. You can enroll it by following the link https://edstem.org/eu/join/JeUzXG using your departmental (cs) email account.
CMP784 is open to all graduate students in our CENG department. Prospective senior undergraduate students may sit in on the class. Non-CENG graduate students, however, should ask the course instructor for approval before the add/drop period. The prerequisites for this course are:
Grading for CMP784 will be based on
|Oct 4||Introduction to Deep Learning|
|Oct 11||Machine Learning Overview|
|Oct 18||Multi-Layer Perceptrons||Practical 1 out|
|Oct 25||Training Deep Neural Networks|
|Nov 1||Convolutional Neural Networks||Practical 1 due, Practical 2 out|
|Nov 8||Understanding and Visualizing CNNs||Project proposal due|
|Nov 15||Recurrent Neural Networks|
|Nov 22||Attention and Memory||Practical 2 due|
|Nov 29||Autoencoders and Deep Generative Models|
|Dec 6||Progress Presentations|
|Dec 13||Deep Generative Models (cont'd.)||Project progress report due|
|Dec 20||Deep Generative Models (cont'd.)|
|Dec 27||Self-supervised Learning|
|Jan 3||Final Project Presentations|