911±¬ÁÏÍø

Content:

Computational skills are essential to many career options for undergraduates, including bioscience postgraduate courses and research.Ìý Modern life science increasingly makes use of computational methods to analyze complex datasets.Ìý In this module, students will learn the skills to write Python code to implement statistical and machine learning algorithms that can be applied in a range of contexts.

Each week the module will cover an aspect of computer coding using examples and exercises that drawn on bioscience contexts.

Topics will include:

• Probability, maximum likelihood, Bayes theorem
• Supervised learning: regression and classification
• Unsupervised learning: dimensionality reduction and clustering
• Model evaluation and improvement
• Reinforcement learning
• Neural networks and deep learning

There will be weekly office hours where students can attend to ask and get help with any coding issues they have encountered.

Prior Python programming experience (e.g. BIOS0030) and basic statistics (e.g. STAT0021) are essential.

Aims:

The aim of the module is to ensure that undergraduate students have an opportunity to gain skills in modern data analysis techniques which are increasingly important across scientific research. This will be taught with a combination of underlying mathematical principles and biological application led examples, to make the course accessible and interesting to bioscience undergraduates.

These skills will be of use to students across their general project work as they progress through their degree, and in particular will allow them to take on computational based final-year projects.

Learning Outcomes:

At the end of the module students will be able to:

• Demonstrate an understanding of fundamental concepts in modern frequentist and Bayesian statistics
• Demonstrate an understanding of fundamental concepts and applications of machine learning
• Demonstrate an understanding of how to process data for input into machine learning analyses
• Demonstrate an understanding of different algorithms across machine learning and of where they are applicable
• Interpret suggestions for how to structure analysis code for data science

Complete an investigation applying the statistical and machine learning skills covered in the lectures, write up findings and put them in context.