CS 559: Deep Learning

Fall 2021

UPDATE:

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.

Homework:
Please follow this link to access the homework details.
 Homework details/materials are accessible only within Bilkent network. Use VPN to access from home.

Literature Survey and Presentation:

Project:

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 21 December 2021
Literature Survey Proposal submission
[subject line: cs559_2021f_survey]
8 October 2021, 23:59
Literature Survey Report submission
[via Moodle]
8 December 2021, 23:59
Literature Survey Presentation (slides) submission
[via Moodle]
10 December 2021, 23:59
Literature Survey Presentation 10 December 2021
Homework submission (including the report)
[via Moodle]
21 November 2021, 23:59
Project Proposal submission
[subject line: cs559_2021f_proj_proposal]
11 October 2021, 23:59
Project Progress Presentation 03 December 2021
Project Progress Report submission
[via Moodle]
1 December 2021, 23:59
Project Final Presentation 28 December 2021
Project submission 
(including the report and presentation)
[via Moodle]
29 December 2021, 23:59

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

Week Topic Lecture Notes
1 Introduction [online]  
2 Basics [online],
Loss Functions [online]
 
 
3 Optimization  
4 Feedforward networks and training  
 
5 Feedforward networks and training
Convolutional neural networks
  >>
 
6 Spatial localization and detection  
7 Spatial localization and detection & Segmentation
Segmentation & Understanding and Visualizing CNNs
 
 
8 No Lecture
9 Recurrent Neural networks
Word Embeddings and Language Models
 
 
10 Unsupervised Learning and Generative Models  
11 Project Progress Presentations  
12 Literature Survey Presentations  
13 Deep reinforcement learning  
14 Midterm
Overview, Q&A
 
15 Project Presentations