Course Content 📋 *

Cover: Hand-drawn illustrations by Santiago Ramón y Cajal, father of modern neuroscience.

#	Topic	Textbook Reading [UDL]	Slides		Programming Assignment	Written Assignment
1	Introduction	Ch. 1, 2	Introduction	Supervised Learning	PA.1.	WA.1.
2	Neural Networks I	Ch. 3	Shallow Neural Networks		PA.2.	WA.2.
3	Neural Networks II	Ch. 4	Deep Neural Networks		PA.3.
4	Loss Functions	Ch. 5	Least Squares, NLL, Cross Entropy		PA.4.	WA.3.
5	Fitting Models	Ch. 6	Gradient Descent		PA.5.	WA.4.
	Exam 1
6	Gradients	Ch. 7	Backpropagation		PA.6.
7	Initialization and Performance	Ch. 8	He Initialization + Bias, Variance and Noise		PA.7.
8	Regularization	Ch. 9	Explicit/Implicit Regularization + Dropout + Ensembling
	Exam 2
9	Convolutional Neural Networks	Ch. 10
10	Transformers	Ch. 12
11	Generative Adverserial Networks	Ch. 15
	Final Exam

* Tentative, subject to change.

Textbooks📚

• [UDL] Understanding Deep Learning, Simon J. D. Prince [PDF 📖] [Web 🌐 ]
• [DDL] Dive into Deep Learning, Aston Zhang, Zachary Lipton et al.[PDF 📖] [Web 🌐]

Other Resources 🗄️

• CSC-272 Data Mining, Fall 2024
• CSC-343 Artificial Intelligence, Spring 2025
• Python: How to Think Like a Computer Scientist (Swarthmore Edition) by Jeffrey Elkner, Allen B. Downey, and Chris Meyers (free, open textbook)

Class Meeting Times 🕣

Lecture: Riley Hall 204
Tuesdays, Thursdays
08:30 AM - 10:00 AM

Lab: Riley Hall 203
Thursdays
2:30 PM - 4:30 PM

Instructor Information 👨🏽‍🏫

Dr. Syed Fahad Sultan
Office: Riley Hall 200-H
Phone: 864-294-3755
Email: fahad.sultan@furman.edu
Web: https://fahadsultan.com
Email: fahad.sultan@furman.edu

Office Hours: 🕰️

No fixed office hours
You can schedule an appointment with me using using this calendly link.

Open door policy, when not in class or meeting
Drop by office, for any other time
OR Email to schedule time

Course Description

This course provides a comprehensive introduction to deep learning, progressing from linear regression to state-of-the-art architectures like transformers. Students will implement fully connected neural networks from scratch to build a solid foundation and explore convolutional neural networks (CNNs), transformers, and generative models. Hands-on experience with modern tools like PyTorch will be emphasized, enabling students to design, train, and evaluate deep learning models for tasks in computer vision, natural language processing, and beyond.

Course Goals

• Understand the theoretical foundations of deep learning and implement feedforward neural networks from scratch.
• Gain hands-on experience using PyTorch to design, train, and evaluate deep learning models.
• Apply convolutional neural networks (CNNs), transformers, and diffusion models to real-world tasks.
• Explore generative models like GANs and VAEs and their applications in AI.
• Build and optimize deep learning solutions for domains such as computer vision and natural language processing.

Grading Scale 💯

(Subject to change,
letter grade +/- at instructor's discretion)

A	grade >= 90%
B	80% <= grade < 90%
C	70% <= grade < 80%
D	60% <= grade < 70%
F	grade < 60%

Grading Specifications

Exam 1	15%
Exam 2	15%
Final Exam	20%
Written Assignments	20%
Programming Assignments	20%
Class Participation	5%
Professionalism	5%

Minimum Requirements:

In order to pass this class, you must
1. Earn ≥ 60% of the total points
2. Attend ≥ 80% of the lectures and labs
3. Submit ≥ 80% of all assignments
4. Take ALL tests and final!
In other words, you cannot blow off an entire aspect of the course and pass this class!
Note that this basic requirement is necessary but not sufficient to pass the class.

Lab Times:

The 2-hour lab sessions will be used to introduce programming problems in the weekly assignments. The submission deadline will extend beyond the 2-hr block. Detailed instructions will be provided with each assignment.

Some General Advice:

• Reach Out: It is to your advantage to communicate with me whether in class, in my office, or via email. I plan to maintain an open-door policy between 8:30 AM -4:30 PM, Monday to Friday, unless I am in a meeting or teaching a class. You are strongly encouraged to visit me in my office or request a meeting via email with any questions, comments or observations about the class.
• Come to class and actively participate!
• The assignments and labs are there for you to help learn and gain confidence. Diligent work on these is going to pay off in exams and in your career.
• Start assignments early. This will allow you time to (a) get stuck and recover (b) seek my help, if needed.
• Do not cheat! It is not worth it. Do not overuse your friends or the internet. Come to my office hours or send me an email instead. I know all the answers and am willing to help.

Professionalism:

The professionalism grade is based on several key factors. This includes attending class on time and demonstrating respect toward others at all times. Maintaining a professional environment also requires refraining from using cell phones during class. Additionally, fostering a respectful and inclusive atmosphere is essential; there is no such thing as a stupid question, and laughing at or ridiculing someone else’s question is completely unacceptable. Such behavior detracts from the supportive environment necessary for all participants to feel comfortable asking questions and engaging in meaningful discussions.

Academic Integrity:

Academic Integrity standards are important to our Furman community and will be upheld in this class. Students should review the Academic Integrity Pledge posted in the classroom and resources available on www.furman.edu/integrity. In this class, the grade penalty for an academic integrity violation is an F for the course. Academic Discipline procedures will be followed through the Office of the Academic Dean.

For programming assignments/homeworks and labs, follow the 50 foot policy in its spirit.

Additional Resources in the Center for Academic Success (CAS; LIB 002):

Peer Tutors are available free of charge for many classes and may be requested by dropping by CAS (LIB 002) or on the Center for Academic Success website. Tutors are typically recommended by faculty and have performed well in the class.

The Writing & Media Lab (WML) is staffed by student Consultants who are trained to help you improve your writing and multimodal communication skills. The consultation process is non-directive and intended to allow students to maintain ownership of their work. In addition to helping with the nuts and bolts, WML Consultants also support you in developing your own ideas thoughtfully and critically, whether you’re writing an essay or planning a video or other multimedia project. You may drop into the WML during its regular hours (LIB 002; 9 AM to 10 PM) or visit the Writing and Media Lab website to make an appointment online.

Professional Academic Assistance Staff in CAS can provide students assistance with time management, study skills, and organizational skills.

The Writing and ESL Specialist provides professional writing support as well as support for students whose primary language is not English.

Accomodations

Furman University recognizes a student with a disability as anyone whose impairment substantially limits one or more major life activity. Students may receive a variety of services including classroom accommodations such as extended time on tests, test proctoring, note-taking assistance and access to assistive technology. However, receipt of reasonable accommodations cannot guarantee success–all students are responsible for meeting academic standards. Students with a diagnosed disability may be entitled to accommodations under the Americans with Disabilities Act (ADA).

Please visit Student Office for Accessibility Resources for more info.

Nondiscrimination Policy and Sexual Misconduct:

Furman University and its faculty are committed to supporting our students and seeking an environment that is free of bias, discrimination, and harassment. Furman does not unlawfully discriminate on the basis of race, color, national origin, sex, sexual orientation, gender identity, pregnancy, disability, age, religion, veteran status, or any other characteristic or status protected by applicable local, state, or federal law in admission, treatment, or access to, or employment in, its programs and activities.

If you have encountered any form of discrimination or harassment, including sexual misconduct (e.g. sexual assault, sexual harassment or gender-based harassment, sexual exploitation or intimidation, stalking, intimate partner violence), we encourage you to report this to the institution. If you wish to report such an incident of misconduct, you may contact Furman's Title IX Coordinator, Melissa Nichols (Trone Center, Suite 215; Melissa.nichols@furman.edu; 864.294.2221).

If you would like to speak with someone who can advise you but maintain complete confidentiality, you can talk with a counselor, a professional in the Student Health Center or someone in the Office of Spiritual Life. If you speak with a faculty member, understand that as a "Responsible Employee" of the University, the faculty member MUST report to the University’s Title IX Coordinator what you share to help ensure that your safety and welfare are being addressed, consistent with the requirements of the law.

Additional information about Furman's Sexual Misconduct Policy, how to report sexual misconduct and your rights can be found at the Furman Title IX Webpage. You do not have to go through the experience alone.