Emily Mower ProvostProfessor, Computer Science and Engineering
menu MENU
Emily Mower Provost
Emily Mower ProvostProfessor, Computer Science and EngineeringComputer Science and Engineering
(734) 647-1802 3629 Beyster Bldg.2260 Hayward St.Ann Arbor, MI 48109-2122

EECS 448: Applied Machine Learning for Modeling Human Behavior

Summary

Everywhere we look, machine learning is uncovering new ways of sensing and modeling human behavior.  But, how does this work?  Does this even work?  The course will cover current practices in measuring and sensing human behavior via machine learning.

Enforced Prerequisites: Students should have taken EECS 281 and (MATH 214 or MATH 217 or MATH 296 or MATH 417) or graduate standing.

Course Description

Machine learning, with a focus on human behavior, across multiple modalities including speech and text. Teams complete projects based primarily on their individual interests centered on modeling an aspect of human behavior. Prior experience with speech/language or other data modeling is not needed.

Learning Objectives

  • Understand the value of human behavior computing in industry and research.
  • Develop an understanding for the common signals used to measure behavior (speech, text, multimodal).
  • Learn machine learning methods in affective computing.
  • Demonstrate an understanding of the concepts by building systems that sense and interpret human behavior.
  • Demonstrate an understanding of the limitations of the technologies critically interpreting the newest advances in human-centered technologies.
  • Understand how python tools can be used in these domains.

Course Evaluation

The evaluation of this course will include four homeworks, a midterm, and a semester-long project.

Lecture-by-Lecture (Winter 2022, subject to change!)

  1. Introduction
  2. Language
  3. Linear Regression and Research Spotlight
  4. Logistic regression and research Spotlight
  5. Probability prep
  6. Gaussian Mixture Models and research spotlight
  7. Audio
  8. Hidden Markov Models 1
  9. Hidden Markov Models 2
  10. Hidden Markov Models 3
  11. Hidden Markov Models 4
  12. Hidden Markov Models Applications
  13. Data collection in the real world
  14. Midterm ← date still to be finalized (approximate only)
  15. Hyperparameter optimization, regularization, feature selection
  16. Neural Networks and human behavior 
  17. Project Milestone Presentation Day
  18. Neural Networks and human attention
  19. Convolutional Neural Networks (CNN) and facial emotion recognition
  20. Recurrent Neural Networks (RNN) and age detection
  21. Multimodal Fusion
  22. Autoencoders and Feature Learning
  23. Representation Learning and Regularization
  24. Transformers in Affective Computing
  25. Anonymization in Human Behavioral Data
  26. Privacy
  27. Project presentations
  28. Project presentations