CS 559: Deep Learning

Spring 2020

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 21%
Literature Survey and Presentation 11% + %5
In-class participation and Attendance 5%
Midterm:Essay/written 20%
Project 38%

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.

Important Dates:

Event Date / Deadline
Midterm Exam 29 April 2020, 10:40-12:30
Literature Survey Proposal submission
[subject line: cs559_2020s_survey]
21 February 2020, 23:59
Literature Survey Report submission
[subject line: cs559_2020s_survey_report]
3 May 2020, 23:59
Literature Survey Presentation 4/6 May 2020
Homework submission (including the report)
[subject line: cs559_2020s_hw]
21 April 2020, 23:59
Project Proposal submission
[subject line: cs559_2020s_proj_proposal]
25 February 2020, 23:59
Project Progress Presentation 20 April 2020
Project Progress Report submission
[subject line: cs559_2020s_proj_progress]
20 April 2020, 23:59
Project Final Presentation 18/20 May 2020
Project submission (including the report)
[subject line: cs559_2020s_proj_final]
3 June 2020, 23:59

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

Week Topic Dates Lecture Notes
1 Introduction 03 February 2020 (08:40-10:30)
05 February 2020 (10:40-12:30)
[w1a] [w1b]
[w1c] [w1d]
2 Optimization 10 February 2020 (08:40-10:30) [w2ab]
3 Feedforward networks and training 17 February 2020 (08:40-10:30)
19 February 2020 (10:40-12:30)
[w3ab]
[w3cd]
4 Feedforward networks and training cont'd,
Convolutional neural networks
24 February 2020 (08:40-10:30)  >>>
[w4ab]
5 Convolutional neural networks cont'd,
Deep learning for spatial localization
02 March 2020 (08:40-10:30)
04 March 2020 (10:40-12:30)
 >>>
[w5cd v03]
6 Deep learning for segmentation 09 March 2020 (08:40-10:30) [w6ab]
7 Understanding and Visualizing CNNs,
Recurrent neural networks
23 March 2020 (08:40-10:30)
25 March 2020 (10:40-12:30)
[w7abc]
[w7d]
8 Recurrent neural networks cont'd,
Word Embeddings and Language Models
30 March 2020 (08:40-10:30)  >>>
[w8b]
9 Word Embeddings and Language Models,
Unsupervised Learning and Generative Models
06 April 2020 (08:40-10:30)
08 April 2020 (10:40-12:30)
 >>>
[w9cd_updated]
10 Deep reinforcement learning 13 April 2020 (08:40-10:30) [w10ab]
11 Project Progress Presentations,
QA Session
20 April 2020 (08:40-10:30)
22 April 2020 (10:40-12:30)

12 Midterm Exam 29 April 2020 (10:40-12:30)  
13 Literature Survey Presentations 04 May 2020 (08:40-10:30)
06 May 2020 (10:40-12:30)

14 No Lecture No Lecture  
15 Project Presentations 18 May 2020 (08:40-10:30)
20 May 2020 (10:40-12:30)