0% found this document useful (0 votes)
72 views4 pages

ESE 577 Syllabus Fall2024

Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
72 views4 pages

ESE 577 Syllabus Fall2024

Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

ESE 577 — Deep Learning

Algorithms and Software


Instructor: Jorge Mendez-Mendez
Fall 2024

1 Lecture
Thursdays 6:30 pm – 9:20 pm, Frey Hall 216. Attendance is mandatory. During
lectures, we will do an overview of the technical contents of the course, tie
together the high-level motivation for the ideas we’ll cover, and go over concepts
in detail.

Recitation A 3-hour lecture is too much for anyone (including myself!). To


alleviate this, we will use the second half of the lecture as recitation, where we
will do exercises on the whiteboard and some Python coding.

2 Office hours
Mondays and Wednesdays, 3:00 pm – 5:00 pm, Light Engineering Building,
Room 145.

3 Course description
This course is an introduction to deep learning which uses neural networks to
extract layered high-level representations of data in a way that maximizes per-
formance on a given task. Deep learning is behind many recent advances in AI,
including Siri’s speech recognition, Facebook’s tag suggestions and self-driving
cars. Topics covered include basic neural networks, convolutional and recurrent
network structures, deep unsupervised and reinforcement learning, and applica-
tions to problem domains like speech recognition and computer vision. Classes
will be a mix of short lectures and tutorials, hands-on problem solving, and
project work in groups. Fall, 3 credits, grading ABCF.

4 Lecture schedule
The following schedule is tentative and subject to change.

1
• 08/29 – Introduction to machine learning, regression, regularization
• 09/05 – Gradient descent
• 09/12 – Logistic regression
• 09/19 – Features

• 09/26 – Neural nets: multilayer perceptrons, backpropagation


• 10/03 – Convolutional neural nets (CNNs)
• 10/10 – Modern neural nets: early stopping, dropout, batch normalization,
skip connections

• 10/17 – Sequential data, recurrent neural nets


• 10/24 – Transformers
• 10/31 – Unsupervised learning

• 11/07 – Markov decision processes (MDPs)


• 11/14 – Reinforcement learning
• 11/21 – Deep reinforcement learning
• 11/28 – No classes (Thanksgiving break)

• 12/05 – The future of deep learning

5 Recommended books
• “Deep learning with Python,” (2nd edition) by François Chollet
• “Deep learning: A visual approach,” by Andrew Glassner
• “Deep learning with Pytorch,” by Eli Stevens, Luca Antiga, and Thomas
Viehmann

• “Deep learning,” by Ian Goodfellow, Yoshua Bengio, and Aaron Courville


• Deep learning has become so popular, that you can find blogs and tutorials
for just about any topic. I encourage students to browse around to find
additional material.

2
6 Grading
The following evaluations will take place throughout the semester:
• 10% quizzes: 14 quizzes, one at the end of every class. I will keep only
the best 10 grades for each stuent.
• 20% homework: approximately 10 homework assignments, roughly weekly

• 20% project: single larger project toward the end of the semester
• 20% midterm: date TBD
• 30% final: date determined by the registrar’s office

Late days Assignments turned in late will receive a penalty of 20% per day.
The full 20% penalty is applied at midnight immediately after the deadline for
each assignment. Each student will be granted three automatic 1-day extensions
on homework assignments.

Collaboration policy Students are responsible for writing their own quizzes,
assignments, projects, and exams. For homework assignments, students are wel-
come (and encouraged) to discuss problems with one peer, but each student
must write their own assignment wrtieup and code individually. The
peer must be listed at the top of the writeup for each assignment.

7 Student Accessibility Support Center State-


ment
If you have a physical, psychological, medical, or learning disability that may
impact your course work, please contact the Student Accessibility Support Cen-
ter, Stony Brook Union Suite 107, (631) 632-6748, or at [email protected].
They will determine with you what accommodations are necessary and appro-
priate. All information and documentation is confidential.
Students who require assistance during emergency evacuation are encour-
aged to discuss their needs with their professors and the Student Accessi-
bility Support Center. For procedures and information go to the following
website: https://ehs.stonybrook.edu/programs/fire-safety/emergency-
evacuation/evacuation-guide-disabilities and search Fire Safety and Evac-
uation and Disabilities.

8 Academic Integrity Statement


Each student must pursue his or her academic goals honestly and be person-
ally accountable for all submitted work. Representing another person’s work

3
as your own is always wrong. Faculty is required to report any suspected in-
stances of academic dishonesty to the Academic Judiciary. Faculty in the Health
Sciences Center (School of Health Technology & Management, Nursing, Social
Welfare, Dental Medicine) and School of Medicine are required to follow their
school-specific procedures. For more comprehensive information on academic
integrity, including categories of academic dishonesty please refer to the aca-
demic judiciary website at http://www.stonybrook.edu/commcms/academic_
integrity/index.html.

9 Critical Incident Management


Stony Brook University expects students to respect the rights, privileges, and
property of other people. Faculty are required to report to the Office of Student
Conduct and Community Standards any disruptive behavior that interrupts
their ability to teach, compromises the safety of the learning environment, or
inhibits students’ ability to learn. Faculty in the HSC Schools and the School
of Medicine are required to follow their school-specific procedures. Further in-
formation about most academic matters can be found in the Undergraduate
Bulletin, the Undergraduate Class Schedule, and the Faculty-Employee Hand-
book.

You might also like