This lesson is in the early stages of development (Alpha version)

Introduction to Machine Learning For Engineering Research (ML4ER)

This curriculum provides students an introduction to using machine learning tools and the associated necessary background on machine learning methods and statistical analysis. Throughout the curriculum, students will focus on using two software tools (Citrination and MAST-ML) to generate machine learning models. They will learn key ideas for assessing model performance and decision making skills for how to improve or modify a model.

It is expected that between synchronous (and asynchronous) meetings, work groups, and completion of activities that students will spend ~9 hours of time on work related to their participation in the Skunkworks Education group each week. This corresponds to approximately a 3 credit hour course if receiving credit for an independent study course.


Students are not expected to have any prerequisite technical skills or knowledge, though familiarity with basic programming concepts and python specifically may provide a smoother transition into using the software tools in this curriculum.


Setup Download files required for the lesson
00:00 1. Basics of Machine Learning What type of research problems can machine learning solve, and what approach do models use to accomplish this?
How does a machine learning model make predictions from its inputs?
What are a set of key steps (also called a workflow) for solving a machine learning research problem?
02:25 2. Establishing Research Workflows What is MAST-ML, and how can it be setup to run on Google Colab?
What is the process of using MAST-ML to execute machine learning workflows?
What advantages does MAST-ML have in developing machine learning models for informatics research?
04:40 3. Comparing Model Types How does MASTML enable users to investigate different options within a machine learning workflow?
Specifically, how do users change the model type, hyperparameters, and define a grid search of hyperparameters?
06:55 4. Optimizing Model Hyperparameters How does MAST-ML enable users to modify the hyperparameters of a model?
Buidling off of the idea of using a grid search of hyperparameters, how can users converge on an optimized model?
09:10 5. Ethical Data Cleaning When is it appropriate to modify data used in machine learning modeling?
When / What types of modifications are not OK?
09:45 6. Navigating Roadblocks and Obstacles What do I do when I get stuck on an activity / assignment?
10:20 7. Creating a Group Compact How can we set up a new group research activity to have a positive experience for all members?
10:55 8. Addressing Model Limitations How do I properly assess my model’s performance and limitations when making new predictions?
11:30 Finish

The actual schedule may vary slightly depending on the topics and exercises chosen by the instructor.