CS58700: Foundations Of Deep Learning (Spring 2024)

Images generated from DALL-E-2 with text prompt A class on Deep Learning, digital art.


Course Information

This course provides an integrated view of the key concepts of deep learning (representation learning) methods. This course focuses on teaching principles and methods needed to design and deploy novel deep learning models, emphasizing the relationship between traditional statistical models, invariant theory, and the algorithmic challenges of designing and deploying deep learning models in real-world applications. This course has both a theoretical and coding component. The course assumes familiarity with coding in the language used for state-of-the-art deep learning libraries, linear algebra, probability theory, and statistical machine learning.

Pre-requisites:

Textbook:

Grading:

The final grade will be curved and no stricter than the cutoff: A+: 97-100, A: 93-96, A-: 90-92, B+: 87-89, ..., etc.
The percentage is computed following (without any rounding):

FAQ:


Instructor & TAs

Raymond A. Yeh

Instructor

Email: rayyeh [at] purdue.edu
Office Hour: Wednesday 9AM-10AM
Location: Zoom

Md Ashiqur Rahman

Teaching Assistant

Email: rahman79 [at] purdue.edu
Office Hour: Monday 11AM-12PM
Location: HAAS 143

Simon Zhang

Teaching Assistant

Email: zhan4125 [at] purdue.edu
Office Hour: Friday 1PM-2PM
Location: HAAS G072


Time & Location

  • Time: Tuesday & Thursday (9:00 am - 10:15 am)
  • Location: Krannert Building G018

Course Schedule

The following schedule is tentative and subject to change.

DateEventDescriptionReadings
Jan 9 Lecture 1 Introduction & Overview

Jan 11 Lecture 2 Supervised Learning

Jan 15 Info. Assignment 1 Released

Select from the following:
Jan 16 Lecture 3 Multilayer Perceptron (MLP)

Jan 18 Lecture 4 Optimization

Jan 23 Info. Cancelled due to weather

Select from the following:
Jan 25 Lecture 5 Training Deep Neural Networks

Jan 30 Lecture 6 How to Read Papers + Invariant MLP

Feb 1 Lecture 7 Invariant MLP Part 2

Feb 2 Deadline Assignment 1 Due (Friday Feb 2, 11:59PM)

Select from the following:
Feb 5 Info. Assignment 2 Released

Select from the following:
Feb 6 Lecture 8 Convolution Neural Network Part 1

Feb 8 Lecture 9 Convolution Neural Network Part 2

Feb 13 Lecture 10 Recurrent Neural Network

Feb 15 Lecture 11 Set Representation Learning

Feb 20 Lecture 12 Graph Neural Network

Feb 22 Lecture 13 Attention Layer + Transformer Architectures

Feb 23 Deadline Assignment 2 Due (Friday Feb 23, 11:59PM)

Select from the following:
Feb 26 Info. Assignment 3 Released

Select from the following:
Feb 27 Lecture 14 Variational AutoEncoder

Feb 29 Lecture 15 Diffusion Model

March 5 Lecture 16 Generative Adversarial Network

March 7 Lecture 17 Structuring Machine Learning Projects

Mar 8 Deadline Assignment 3 Due (Friday Mar 8, 11:59PM)

Select from the following:
Mar 8 Deadline Project Proposal Due (Friday Mar 8, 11:59PM)

Select from the following:
March 12 --- Spring Break

Select from the following:
March 14 --- Spring Break

Select from the following:
March 19 Lecture 18 Midterm Review

March 21 Exam Midterm (In class)

Select from the following:
March 25 Info. Assignment 4 Released

Select from the following:
March 26 Lecture 19 Optimization Layers

March 28 Lecture 20 Hyperparameter optimization

Apr 2 Lecture 21 Meta Learning

Apr 4 Lecture 22 Self-supervised learning

Apr 5 Deadline Assignment 4 Due (Friday Apr 5, 11:59PM)

Select from the following:
Apr 8 Info. Assignment 5 Released

Select from the following:
Apr 9 Lecture 23 Applications--- 3D Vision

Apr 11 Lecture 24 Applications--- Language and Vision

Apr 16 Lecture 25 Applications--- Detection & Segmentation

Apr 18 Lecture 26 Final Project Presentation 1

Apr 19 Deadline Assignment 5 Due (Friday Apr 19, 11:59PM)

Select from the following:
Apr 23 Lecture 27 Final Project Presentation 2

Apr 25 Lecture 28 Final Project Presentation 3

Apr 30 Deadline Final Project Report Due (Tuesday April 30, 11:59PM)

Select from the following:

Policies

Late & Absence Policy

We do not accept late assignments, i.e., late assignment by a second will be counted as 0%. For the consistency and fairness to all students, we follow the policy and absence request through the Office of the Dean of Students.

Academic Honesty

Please refer to Purdue's Student Guide for Academic Integrity. Academic dishonesty will result in an automatic zero on an assignment (not droppable) and the course grade will be reduced by one full letter grade. A second attempt will result in a failing grade for the course. It is one's responsibility to prevent others from copying your work.

Accessibility

Purdue University strives to make learning experiences as accessible as possible. If you anticipate or experience physical or academic barriers based on disability, please contact the Disability Resource Center at: drc@purdue.edu or by phone at 765-494-1247 and the course instructor to arrange for accommodations.

Classroom Guidance Regarding Protect Purdue

Any student who has substantial reason to believe that another person is threatening the safety of others by not complying with Protect Purdue protocols is encouraged to report the behavior to and discuss the next steps with their instructor. Students also have the option of reporting the behavior to the Office of the Student Rights and Responsibilities. See also Purdue University Bill of Student Rights and the Violent Behavior Policy under University Resources in Brightspace.

University Policies

Please refer to additional university policies in BrightSpace.