| |
COL 775/COL 7375: Deep Learning
(Semester II, 2025-26)
General Information
Semester: Sem II, 2025-26.
Instructor: Parag Singla (email: parags AT cse.iitd.ac.in)
Class Timings/Venue:
- Slot C. Tuesday, Wednesday, Friday: 8 am - 9 am.
- Venue: LHC 526
Teaching Assistants:
To be Announced.
Class List and TA Assignment: Coming soon!
Sign up for Piazza
Code: as annouced over email
Pre-requisites
A foundational course in AI or ML.
Announcements
[Mar 31, 2026]: Assignment 2 (Part A) released. Parts B and C will be released soon.
[Mar 13, 2026]: Assignment 1 (Part 2) released.
[Feb 15, 2026]: Past Year Papers uploaded for Practice.
[Jan 18, 2026]: Course website is up!
[Jan 2, 2026]: First Class!
Obective:
This course is meant to be the first graduate level course in deep learning. Deep Learning is
an emerging area of Machine Learning which has revolutionized the progress in the field during
last few years with applications found in NLP, Vision and Speech to name a few domains. This
course is intended to give a basic overview of the mathematical foundations of the field, and
present a number of techniques/arhitectures which have become de-facto standard for a large number
of applications in vision, NLP and other areas. We will also touch upon some of the recent advances
in the field. become basis for more advanced ones. Without an implementation, no
deep learning class can be complete. Students will get to implement some of the architectures on
a GPU to test on large datasets.
Content: Basics: Introduction. Multi-layered Perceptrons. Backpropagation. Regularization. Dropouts.
Optimization: Challenges. Stochastic Gradient Descent. Advanced Optimization
Algorithms. Batch and Layer Normalization. Convolutional Networks (CNNs). Pre-trained networks.
Recurrent Architectures. Transformers. Generative Architectures. Graph Neural Networks. Deep Reinforcement
Learning. Advanced Topics.
Week-Wise Schedule (to be refined as we progress in the semester)
NOTE: The exact list of topics below is tentative (until we are past that week).
We will update it as we go through the lectures in each week. So, stay tuned!
| Week | Topic | Book Chapters/Supplementary Notes | Class Notes, Other Resources |
| 1 | Introduction, Motivation | |
Jan 2, Jan 6
|
| 2,3 | Mulit-layered Perceptrons, Backpropagation | Goodfellow et al. Chapter 6 |
Jan 7,
Jan 9,
Jan 10,
Jan 13,
Jan 16
|
| 3,4 | Regularization, Optimization Techniques. | Goodfellow et al. Chapter 7,8 |
Jan 20,
Jan 21,
Jan 23,
Jan 27,
Jan 30
|
| 5 | Batch Normalization, Dropouts | Goodfellow et al. Chapter 7.12 (Dropouts) |
Feb 4
Batch Normalization,
Dropouts
|
| 6 | Deep Learning for Vision - Basic Models (CNNs), ResNet | Goodfellow et al. Chapter 9 |
Feb 6,
Feb 10,
Feb 11
CNN Slides ,
AlexNet,
ResNet
|
| 7 | Deep Learning for NLP - Basic Models (RNNs,LSTM) | Goodfellow et al. Chapter 10 |
Feb 13,
Feb 17
Bahdanau Attention (Feb 18)
|
| 8 | Deep Learning for NLP (Attention), Transformers | |
Mar 10,
Mar 11,
Mar 13, see list of papers.
|
| 9 | Transformers - continued | |
see list of papers |
| 10 | Generative Models (GPT Series) | |
see list of papers |
| 11 | Vision Transformers, Handling Multimodality | |
see list of papers |
| 12 | VAEs, GAN | |
April 10,
April 15,
see list of papers
|
| 13 | Diffusion Models | |
see list of papers |
| 14 | Deep Networks for Graphical Data | |
see list of papers |
Link to content/list of papers covered
| Chapters 1 - 5, Goodfellow et al. |
- Deep Learning. Ian Goodfellow, Yoshua Bengio and Aaron Courville. 2016.
Assignment Submission Instructions
- You are free to discuss the problems with other students in the class. But the final solution/code that you
produce should come through your individual efforts.
- Required code should be submitted using Moodle Page.
- Honor Code: Any cases of copying will be awarded a zero on the assignment. Additional
penalities will be imposed based on the severity of copying. Any copying cases run the chances of being
escalated to the Department/DISCO.
- Late policy: You are allowed a total of 3 buffer days (combined) for the all but the last programming
assignment. There is no penalty if your submission stays within the limit of the 3 buffer days
(total). For each additional day beyond the allowed 3 buffer days, you will lose 10% of the score for every
late day in submission. Since last assignment will likely have a competitive part (to be communicated later), buffer days may not be
applicable. We will update with more details as get closer to assignments.
Practice Questions
Assignments
- Assignment 2 Due Date: Thursday May 7, 2026. 11:59 pm.
- Assignment 1 (both parts). Due Date: Thursday March 26, 2026. 11:59 pm.
| Assignment 0 (tentative) | 0% |
| Assignment 1 (Part A, Part B) | 15% |
| Assignment 2 (Project) | 20% |
| Minor | 25% |
| Major | 40% |
AUDIT Pass Criteria: Equivalent of (B-)
|