Foundations of Artificial Intelligence and Machine Learning (AI/ML)

Designed for managers, management track, engineers, and technical professionals who need to make decisions about AI/ML related projects and have limited prior experience in AI and machine learning. In this comprehensive course, participants will achieve an understanding of fundamental machine learning concepts, including the advantages and pitfalls of common strategies.

The course will provide the distinction between supervised and unsupervised learning, classification and regression problems, dimension reduction, and clustering challenges. Participants will also gain insights into, data acquisition, data preprocessing/labeling, dataset size, different model types and optimization criteria.

• Engineers
• Scientists
• Managers / Management Track / Management Trainees, Team Leaders & Technical Professionals
  • with prior experience in calculus, linear algebra, and statistics.

     

At the completion of this course, participants will be able to:

1. Describe advantages and pitfalls in commonly used machine learning strategies.
2. Describe considerations in data collection and prep for machine learning
3. Explain the differences between commonly used models.
4. Describe tradeoffs between dataset size and machine learning model complexity.
5. Give examples of optimization criteria for training machine learning models.
6. Describe the best practices for using data to both train a machine learning model and predict performance.
7. Describe the best practices for optimizing complexity of a machine learning model.

This course is part of the Technical Leadership Certificate. Course may be taken individually as well.

Week 1

Module 1: Introduction to AI & ML Problems

1. Data representation and key features of ML pipelines
2. Data acquisition and preprocessing example
3. Supervised and unsupervised Learning
4. Classification and regression problems
5. Dimension reduction and clustering problems
6. Examples of machine learning approaches

Module 2: Models for Supervised Learning

1. Supervised learning review
2. Linear models
3. Nonlinear models
4. Neural network principles

Week 2 

Module 3: Training Models and Performance Estimation

1. Supervised learning and machine learning models review
2. Model selection and performance analysis
3. Gradient based optimization methods
4. Methods for controlling model overfitting
5. Criteria for optimization of classification models
6. Multiclass classification criteria
7. Backpropagation for training neural networks

Module 4: Clustering and Dimension Reduction

1. Unsupervised learning review
2. Clustering methods
3. Dimensionality reduction, information extraction, and noise reduction

Barry Vanveen

Barry D. Van Veen (S’81-M’86-SM’97-F’02) was born in Green Bay, WI. He received the B.S. degree from Michigan Technological University in 1983 and the Ph.D. degree from the University of Colorado in 1986, both in electrical engineering. He was an ONR Fellow while working on the Ph.D. degree.

He has been with the Department of Electrical and Computer Engineering at the University of Wisconsin-Madison since 1987 and is currently Lynn H. Matthias Professor of Electrical and Computer Engineering. His research interests include signal processing for sensor arrays, biomedical applications of signal processing and machine learning, and instructional methods for improving STEM education.

Dr. Van Veen was a recipient of a 1989 Presidential Young Investigator Award from the National Science Foundation and a 1990 IEEE Signal Processing Society Paper Award. He served as an associate editor for the IEEE Transactions on Signal Processing and on the IEEE Signal Processing Society’s Statistical Signal and Array Processing Technical Committee and the Sensor Array and Multichannel Technical Committee. He received the Byron Bird Award for Excellence in a Research Publication from the College of Engineering in 2020.

In recognition of outstanding teaching, Dr. Van Veen received the 1997 Holdridge Teaching Excellence Award from the ECE Department, the 2014 Spangler Award for Technology Enhanced Instruction from the College of Engineering, the 2015 Chancellor’s Distinguished Teaching Award, and the 2017 Benjamin Smith Reynolds Award for Teaching Engineers at the University of Wisconsin.  He coauthored “Signals and Systems,” (1st Ed. 1999, 2nd Ed., 2003 Wiley) with Simon Haykin and is the Chief Education Officer at AllSignalProcessing.com, a website devoted to signal processing instruction. Dr. Van Veen is a Fellow of the IEEE.