CS 559: Deep Learning

Fall 2023


Catalog Description: Overview of machine learning and its applications. Loss functions, numerical optimization and back-propagation. Fundamentals of feedforward neural networks. Modern architectures and techniques for training deep networks. Convolutional neural networks: basics, visualization, and techniques for efficient spatial localization in images. Recurrent neural networks and their variants. Applications of recurrent neural networks in language and image understanding, and image captioning. Recent advances in generative models learning, generative adversarial networks and variational auto encoders. Unsupervised and self-supervised representation learning. Deep reinforcement learning.

Recommended Books:

Assessment Methods:

Homework 20%
Literature Survey and Presentation 10% + %5
Midterm:Essay/written 30%
Project 35%

Any of the following will directly result in an F grade:

Passing Grade: No predetermined grade to pass the course.

Makeup Policy: Medical report holders will be entitled for the midterm make up. Makeup exam will be comprehensive.


Literature Survey and Presentation:


Template for the Reports:
All reports (including homework report) must be prepared using the IEEE double-column transactions article template (i.e. "bare_jrnl.tex").

Important Dates:

Event Date / Deadline
Midterm Exam TBD
Literature Survey Proposal submission
[subject line: cs559_2023f_survey]
29 September 2023, 23:59
Literature Survey Report submission
(including the presentation)
[via Moodle]
Literature Survey Presentation TBD
Homework submission (including the report)
[via Moodle]
Project Proposal submission
[subject line: cs559_2023f_project]
2 October 2023, 23:59
Project Progress Presentation TBD
Project Progress Report submission
(including the report and presentation)
[via Moodle]
Project Final Presentation TBD
Project submission 
(including the report and presentation)
[via Moodle]

Tentative Schedule & Lecture Notes:
Lecture notes below are downloadable only within Bilkent network. Use VPN to access from home.

Week Topic Dates Lecture Notes
Introduction 15 September 2023 (13:30-15:20)  
2 Basics,
Loss Functions
20 September 2023 (08:30-10:20)
22 September 2023 (13:30-15:20)
 3 Optimization
Feedforward networks and training
27 September 2023 (08:30-10:20)
29 September 2023 (13:30-15:20)
4 Convolutional neural networks 04 October 2023 (08:30-10:20)

5 No Lecture

6 Spatial localization and detection

7 Segmentation

8 Understanding and Visualizing CNNs

9 Recurrent Neural networks

10 Word Embeddings and Language Models

11 Unsupervised Learning and Generative Models

12 Literature Survey Presentations

13 Deep reinforcement learning

14 Q&A; Overview
Project Presentations