This four class course is designed to introduce attendees to central concepts in machine learning as well as examples of applications in biomedical research. Each one hour lecture will emphasize conceptual and practical aspects of machine learning paradigms, explore the foundations of underlying mechanisms, and look at current or potential applications through examples or case studies. The course assumes a solid foundation in basic statistics, but does not assume any prior coding experience. At the end of this course, you will be able to understand the core differences between different forms of machine learning and consider their application with respect to a variety of problem spaces. This course (or equivalent knowledge/preparation) is intended as a prerequisite for future courses covering machine learning skills in both R and Python.
Required software: You are not required to bring a laptop computer to this course, although it may be useful for referencing supplemental material. A mobile device (smartphone or tablet) will be needed for signing in to the course at the beginning of each session; bookmark this link as it will be used to share links and resources: https://hackmd.io/@k8hertweck/conceptsML
- Class 1: Introduction and Conceptual Overview of Machine Learning Concepts
- Class 2: Supervised Learning via Regression and Classification
- Class 3: Unsupervised Learning via Dimensionality Reduction and Clustering
- Class 4: Experimental Design and Ethics in the Machine Learning Process
- Each class's materials are described in the markdown file prefaced with the number of the class.
solutions/includes the answers for all exercises presented in each classinstructors.mdincludes information for instructors to facilitate teaching each lessonhackmdio.mdis an archive of the interactive webpage used during lessons
Much of the material for these lessons has been adapted from these sources as well as those referenced in specific files: