An Introduction to Machine Learning
Sudhakaran Prabakaran, Matt Wayland and Chris Penfold
1 About the course
Machine learning gives computers the ability to learn without being explicitly programmed. It encompasses a broad range of approaches to data analysis with applicability across the biological sciences. Lectures will introduce commonly used algorithms and provide insight into their theoretical underpinnings. In the practicals students will apply these algorithms to real biological data-sets using the R language and environment.
During this course you will learn about:
- Some of the core mathematical concepts underpinning machine learning algorithms: matrices and linear algebra; Bayes’ theorem.
- Classification (supervised learning): partitioning data into training and test sets; feature selection; logistic regression; support vector machines; artificial neural networks; decision trees; nearest neighbours, cross-validation.
- Exploratory data analysis (unsupervised learning): dimensionality reduction, anomaly detection, clustering.
After this course you should be able to:
- Understand the concepts of machine learning.
- Understand the strengths and limitations of the various machine learning algorithms presented in this course.
- Select appropriate machine learning methods for your data.
- Perform machine learning in R.
- Some familiarity with R would be helpful.
- For an introduction to R see An Introduction to Solving Biological Problems with R course.