Spring 2026 CS444/ECE494 Deep Learning for Computer Vision

J. Cornell, Cockatoo with Watch Faces

Overview: This course will provide an elementary hands-on introduction to neural networks and deep learning. Topics covered will include: linear classifiers; multi-layer neural networks; back-propagation and stochastic gradient descent; convolutional neural networks and their applications to computer vision tasks like object detection and dense image labeling; generative modeling (diffusion models); sequence modeling with recurrent networks and transformers; large language models and vision-language models. Coursework will consist of programming assignments in Python (primarily PyTorch) and CBTF exams. Those registered for 4 credit hours will have to complete a project. Instructor: Svetlana Lazebnik (slazebni -at- illinois.edu) Lectures: T TH 11AM-12:15PM, 2079 Natural History Building Lectures will be recorded for later asynchronous viewing. Access to recordings requires illinois.edu login.

TAs: Kulbir Ahluwalia (ksa5), Ozgur Kara (ozgurk2), Jay Mahajan (jaym2), Kiet Nguyen (kietan2), Jason Vega (javega3)

Instructor and TA office hours: See Campuswire (and always check announcements for any last-minute changes)

Contacting the course staff: For emergencies and special circumstances, please email the instructor. For questions about lectures and assignments, use the discussion board. For questions about your scores (including regrade requests), email the responsible TAs.

Prerequisites: Multi-variable calculus, linear algebra, data structures (CS 225 or similar), statistics (CS 361, STAT 400, or similar).

Grading scheme:

	3 credits	4 credits
Programming assignments	60%	45%
Exams	40%	30%
Project		25%

• Programming assignments:
  • Can optionally be done in pairs -- but see important disclaimers on group work!
  • Will be using PyTorch and Google Colab
• Exams:
  • There will be two 50-minute CBTF midterm exams and one 1 hour 50 minute final. The midterms will be non-cumulative and the final will be cumulative. All exams will consist of multiple choice questions and will be closed book, closed notes.
• Project: for 4-credit students
• Participation extra credit: up to 3% bonus on the cumulative course score will be offered for active in-class and discussion board participation