Course Information

About

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.

Time and Location

Lectures: Thursday at 09:30-12:30 (D5)

Communication

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/NzaJ9r using your departmental (cs) email account.

Prerequisites

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:

  • Programming (you should be a proficient programmer to work out the practicals and to implement your course project.)
  • Calculus (differentiation, chain rule) and Linear Algebra (vectors, matrices, eigenvalues/vectors)
  • Basic Probability and Statistics (random variables, expectations, multivariate Gaussians, Bayes rule, conditional probabilities)
  • Machine Learning (you can still survive this course without a machine learning course before, but it is highly recommended. Some introductory ML courses are BBM406 Fundamentals of Machine Learning and CMP712 Machine Learning. CMP684 Neural Networks is also very related.)
  • Optimization (cost functions, taking gradients, regularization)

Course Requirements and Grading

Grading for CMP784 will be based on

  • Math Prerequisites Quiz (3%) (Each student must complete and pass this quiz!)
  • Practicals (16%) (2 practicals x 8% each)
  • Final Exam (25%)
  • Course Project (presentations and reports) (32%),
  • Paper Presentations (15%),
  • Weekly Quizzes (9%),

Reference Books

  • Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016 (draft available online)

Schedule

Date Topic Assignments
Sep 26 Introduction to Deep Learning
Oct 3 Machine Learning Overview
Oct 10 Multi-Layer Perceptrons Practical 1 out
Oct 17 Training Deep Neural Networks
Oct 24 Convolutional Neural Networks Practical 1 due, Practical 2 out
Oct 31 Understanding and Visualizing CNNs Project proposal due
Nov 7 Recurrent Neural Networks
Nov 14 Attention and Transformers Practical 2 due
Nov 21 Autoencoders and Deep Generative Models
Nov 28 Progress Presentations
Dec 5 Deep Generative Models (cont'd.) Project progress report due
Dec 12 Deep Generative Models (cont'd.)
Dec 19 Self-supervised Learning
Dec 26 Final Project Presentations
Detailed Syllabus and Lectures