Introduction to Deep Learning (EE 60572)
Syllabus

Dept. of Electrical Engineering
University of Notre Dame

Description: This is a survey course on deep learning for first year engineering graduate students. The course topics include 1) Learning from Example, 2) Statistical learning theory, 3) Neural network model (peceptron, multi-layer perceptron, deep models), 4) training pipelines for neural networks, 2) Convolutional Neural Networks for Image Processing, 3) Recurrent and Transformer Models for Sequence Data and Natural Language Processing, 4) Generative Models (Autoencoders, GANs, and Diffusion), 5) Security/Fairness in Machine Learning, and 6) Reinforcement Learning (Deep Q Networks and Actor-Critic Models) The course makes extensive use of TensorFlow/Keras deep learning libraries.

Prerequisites:Students should have prior course work in linear algebra and random processes. Students must have prior Python programming experience.

Textbooks:
TOPICS
  • Introduction - Learning by Example
  • Generalization - a statistical approach
  • Neural Networks Models
  • Deep Neural Network Training Pipeline
  • Convolutional Neural Networks
  • Recurrent Models and Transformers
  • Generative Models
  • Security/Fairness in Machine Learning
  • Deep Reinforcement Learning

Grading: Grades will be based on 8 Homework assignments (40%). There will be two midterms (30%) and final exam or project (30%). Project will be final paper/notebook subject to instructor approval. Homeworks and Exams will be a combination of essay questions, traditional problem solving, and programming exercises.

Instructor:Michael Lemmon,Fitzpatrick 266, lemmon at nd.edu