ECE 8550 Artificial Intelligence

An introductory course designed to immerse beginners into the world of deep learning using PyTorch, providing hands-on experience in developing various types of deep neural networks.

Revised on 12/20/2024

For the definitive and up-to-date course details, please refer to the syllabus on Canvas.

Course overview

ECE 8550 Artificial Intelligence is an introductory course on deep learning with PyTorch. It gives students hands-on experience developing several types of neural networks and examines current issues in AI.

Course description

Students implement fully connected, convolutional, and recurrent neural networks. The course covers PyTorch programming, neural-network training and tuning, and technical and ethical issues in AI, including security, privacy, safety, and explainability.

Topics covered

  • Deep neural networks
    • Fully connected neural networks
    • Convolutional neural networks
    • Recurrent neural networks
  • PyTorch programming
  • Training and tuning deep neural networks
  • Deep learning frontiers
  • Trustworthy AI (e.g., security, privacy, safety, explainability)

Prerequisites

  • ECE 4420/6420
  • College Calculus and Linear Algebra
  • Basic Probability and Statistics
  • Machine Learning basics
  • Python programming skills (Numpy, Pandas, Scikit-Learn)

Recommended Python resources:

Course materials

No textbooks are required for this course. Recommended for after-class reading:

  • Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola. (2020). Dive into Deep Learning. Available Online

Grading criteria

  • Homework
  • Paper reading
  • Final project
  • Attendance

Late policy

  • On the due date, the cutoff for on-time submission is 11:59 pm (Eastern Time).
  • Late work is discounted 5% per calendar day late.
  • Late submissions are not accepted after seven calendar days past the original due date and are graded as zero.