Introduction to Deep Learning

Dept. of Electrical Engineering
University of Notre Dame


Spring 2025- Enroll in Course Number EE 60572-01
Location/Time: TBD

Course Vault
Description: Deep learning technologies have matured to the point where all system engineers must be aware of their capabilities and limitations. Deep learning has demonstrated spectacular success in computer vision, timeseries forecasting, text/language analysis, and autonomous robots. This course uses the TensorFlow/Keras development framework to provide a hands-on introduction to deep learning. The course topics are learning-by-example problem statement, generalization (statistical approach), perceptrons (linear models), multi-layer perceptrons (MLP), training pipelines, convolution models for computer vision, natural language processing (recurrent neural networks and transformers), Generative learning (variational autoencoders, generative pre-trained transformers, diffusion models), reinforcement learning (deeq Q networks and adaptive-critic methods), privacy and fairness in machine learning.
Prerequisites: Python programming experience, probability and linear algebra.
Grading: 15% 4 takehome quizzes, 15% 6 notebook assignments, 20% Final Project, 20% Midterm, 30% Final
Textbooks:
  • Dept. of EE, Univ. of Notre Dame, Introduction to Deep Learning, class lecture notes, Spring 2025
  • (RECOMMENDED) Francois Chollet, Deep learning with Python, 2nd edition, Manning, 2021.
  • (RECOMMENDED) Ian Goodfellow, Yoshua Bengio, Aaron, Courville, Deep Learning MIT Press, 2016.
Instructor: Michael Lemmon, Dept. of Electrical Engineering, University of Notre Dame, Fitzpatrick 275C, (lemmon at nd.edu)