Credits: 3

Description

Prerequisite: ENME392; or permission of instructor.
Restriction: Permission of ENGR-Mechanical Engineering department.
Credit only granted for: ENME440, ENME808E, or ENME743.
Learn how to apply techniques from Artificial Intelligence and Machine Learning to solve engineering problems and design new products or systems. Design and build a personal or research project that demonstrates how computational learning algorithms can solve difficult tasks in areas you are interested in. Master how to interpret and transfer state-of-the-art techniques from computer science to practical engineering situations and make smart implementation decisions.

Semesters Offered

Fall 2017, Fall 2018, Fall 2019

Learning Objectives

  • Week 1: Introduction and Visualization
  • Week 2: Modeling Similarity
  • Week 3: How do we know when our model is good?
  • Week 4: Linear Models - Unsupervised
  • Week 5: Linear Models - Supervised
  • Week 6: Adding Complexity - Kernels
  • Week 7: Adding Complexity - Ensembles
  • Week 8: Adding Complexity - Adaptive Basis Functions
  • Week 9: Probabilistic Models - Porbability Basics
  • Week 10: Probabilitistic Models - Generalized Linear Models
  • Week 11: Probabilitistic Models - Leveraging Probability for Model Improvement
  • Week 12: Control - Reinforcement Learning
  • Week 13: Control - State Estimation; Thanksgiving
  • Week 14: Special Topics
  • Week 15: Special Topics - Expo/Presentations

 

Topics Covered

  • an ability to apply knowledge of mathematics, science, and engineering
  • an ability to design and conduct experiments, as well as to analyze and interpret data
  • an ability to design a system, component, or process to meet desired needs within realistic constraints such as economic, environmental, social, political, ethical, health and safety, manufacturability, and sustainability
  • an ability to identify, formulate, and solve engineering problems
  • an understanding of professional and ethical responsibility
  • an ability to communicate effectively
  • a recognition of the need for, and an ability to engage in life-long learning
  • an ability to use the techniques, skills, and modern engineering tools necessary for engineering practice

Additional Course Information

Instructor 

Fuge, Mark D.

Textbook 

None required.

Optional Recommended Textbooks:
  • Kevin Murphy, Machine Learning: A Probabilistic Perspective, MIT Press
  • Stuart Russell, Peter Norvig, Artificial Intelligence: A Modern Approach, Prentice Hall
  • Christopher Bishop, Pattern Recognition and Machine Learning, Springer
  • Richard Sutton and Andrew Barto, Reinforcement Learning: An Introduction, MIT Press
  • Tom Mitchell, Machine Learning, McGraw Hill

Class/Laboratory Schedule 

  • Two 75 minute lectures each week
Last Updated By 
Dr. Mark Fuge, June 2017