This lesson is being piloted (Beta version)

Machine Learning for Biologists

The Machine Learning for Biologists (ML4Bio) workshop is aimed at biologists with no previous machine learning experience and minimal computational experience. This workshop is designed to teach machine learning concepts, not how to implement machine learning models. After the workshop, participants will be able to define machine learning concepts like samples, features, training set, validation set, test set, evaluation metrics, and model selection. Participants will be able to interactively develop an understanding of machine learning classifiers commonly used in biology like decision trees, random forests, logistic regression, and neural networks. The focus will be on problems in biology where machine learning is effectively used.

The ML4Bio workshop materials are still in development. Feedback is welcome in the GitHub issues.

Getting Started

This is not a programming workshop. You will not be taught how to code or implement machine learning models. This workshop can help you understand machine learning concepts. The goal is to provide you with resources to enable you to engage in conversations about machine learning, read articles that use machine learning, and understand the research methodology at a high level. The workshop uses point-and-click software without requiring any coding. This workshop focuses on supervised machine learning and classification.

To get started, follow the directions in the Setup page to access the required software and data for this workshop.

Schedule

Setup Download files required for the lesson
00:00 1. Introduction What is machine learning?
00:35 2. Classifying T-cells What are the steps in a machine learning workflow?
01:20 3. Evaluating a Model How do you evaluate the performance of a machine learning model?
01:50 4. Decision Trees, Random Forests, and Overfitting How do decision trees and random forests make decisions?
02:30 5. Logistic Regression, Artificial Neural Networks, and Linear Separability What is linear separability?
03:15 6. Understanding Machine Learning Literature How are machine learning workflows presented in research papers?
04:15 7. Conclusion and next steps Where can you learn more about machine learning?
05:00 Finish

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