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 will particularly focus on computer vision problems. The course is taught by Aykut 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 three lectures, each week a student will present a paper related to the topics of the week.
Time and Location
Lectures: Wednesday at 13:15-16:00 (Room D6)
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 Piazza. Please enroll it by following the link https://piazza.com/hacettepe.edu.tr/spring2017/cmp722.
Pre-requisites
CMP722 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)
- Computer Vision (suggested related courses are BBM416 Fundamentals of Computer Vision and CMP719 Computer Vision.)
- 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 CMP722 will be based on
- Practicals (30%) (3 practicals x 10% each)
- Course Project (presentations and reports) (40%),
- Paper Presentations (15%),
- Weekly Quizzes (9%),
- Lecture Summary Notes (6%).
Schedule
| Date | Topic | Assignments |
| Feb 15 | Introduction to Deep Learning | |
| Feb 22 | Machine Learning Overview | |
| Mar 1 | Multi-Layer Perceptrons | Practical 1 out |
| Mar 8 | Training Deep Neural Networks | |
| Mar 15 | Convolutional Neural Networks | Practical 1 due, Practical 2 out |
| Mar 22 | Understanding and Visualizing CNNs | Project proposal due |
| Mar 29 | Recurrent Neural Networks | |
| Apr 5 | Attention and Memory | Practical 2 due, Practical 3 out |
| Apr 12 | Project Progress Presentations | |
| Apr 19 | Representation Learning | Project progress report due |
| Apr 26 | Autoencoders and its variants | Practical 3 due |
| May 3 | Deep Generative Models | |
| May 10 | Deep Reinforcement Learning | |
| May 17 | Final Project Presentations |
Resources
Reference Books
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016 (draft available online)
Similar Courses
- CS231n: Convolutional Neural Networks for Visual Recognition, Fei-Fei Li, Andrej Karpathy, Justin Johnson, Stanford University
- CSC2523: Deep Learning in Computer Vision, Sanja Fidler, University of Toronto
- CSC321: Introduction to Neural Networks and Machine Learning, Tijmen Tieleman, University of Toronto
- Deep Learning, Yann LeCun, New York University
- ECE 6504 Deep Learning for Perception, Dhruv Batra, Virginia Tech
- Machine Learning, Nando de Freitas, Oxford University