CSE 4311 - Neural Networks and Deep Learning

Spring 2025
Lectures: MWF 10:00am-10:50am
Modality: Hybrid.
Classroom: GACB 105.

• The plan is for all lectures to be held both face-to-face (at GACB 105) and online. Any exceptions will be announced via e-mail and on Canvas.
• Students can choose how to attend every lecture. Options include attending in person, attending live using Microsoft Teams, or viewing an offline recording of the lecture on Microsoft Teams.

This course offers an introduction to neural networks and deep learning. Topics include perceptrons, single-layer neural networks, multi-layer neural networks, Tensorflow and Keras, convolutional neural networks, transfer learning, deep learning methods for image classification, and sequential learning models for analyzing text. Auto-encoders and generative adversarial networks will be covered to some extent, as time permits. A strong programming and algorithmic background is assumed, as well as familiarity with linear algebra (vector and matrix operations). Prerequisites: Admitted into an Engineering Professional Program. C or better in each of the following: CSE 3318 (Algorithms), and CSE 3380 or MATH 3330 (Linear Algebra).

Links

• Schedule and Lecture Slides

• Assignments

• Additional Resources

Modality

Lectures: The plan is for all lectures to be held both face-to-face and online. Any exceptions will be announced via e-mail and on Canvas. Students can attend each lecture in person, or live online using Microsoft Teams. In-person attendance for the two midterms is mandatory. Either type of attendance is optional for other lectures. The video recordings will be posted on Teams as well for offline viewing.

Internet and computer requirements: Homework assignments need to be submitted on Canvas. There are significant penalties for late submissions (1 out of 100 points deducted per hour past the deadline). Students taking this class assume full responsibility for having adequate Internet connectivity to view lectures (live or recorded) and to submit assignments on time. Students also assume full responsibility for having access to a computer that is adequate for implementing and running the programming assignments. No accommodations will be provided for students who cannot meet these requirements.

Course web page: https://athitsos.utasites.cloud/courses/cse4311_spring2025/
Lecture times: MWF 10:00am-10:50am
Textbook: Deep Learning with Python, 2nd edition, by François Chollet, 2021.

Instructor:

Vassilis Athitsos

Office hours: MW 11:00am-12:30pm.

Teaching assistants:

Evan Cornish
E-mail: evan.cornish@mavs.uta.edu
Office hours (via Microsoft Teams, or in person at ERB 309): TuTh 5pm-6pm, Fri 1pm-2pm.

Rodrigo Pleitez
E-mail: rodrigo.hernandez-pleite@mavs.uta.edu
Office hours (via Microsoft Teams, or in person at ERB 407): Mondays 2:30pm-3:30pm, TuTh 12pm-1:00pm.