A machine learning short course for the HDRUK-Turing PhD Programme in Health Data Science.
This project is maintained by cwcyau
This is a repo for the Machine Learning training series for the Year 1 Cohort of the HDRUK-Turing PhD Programme in Health Data Science.
The purpose of this course is to provide students with an overview of the cutting edge ideas in modern machine learning with a focus on probabilistic approaches based on Bayesian methodology. This course is not intended to teach you Bayesian modelling in its entirety in these eight sessions. Instead, we will focus on providing a platform to support further detailed learning in your own time by reviewing key aspects of the field and how they apply in health applications and examining the potential developments that may require your attentions.
The course consists of eight parts which are summarised below. Please check each individual part for course pre-requisites and pre-reading.
1. Introduction to Bayesian Machine Learning by Christopher Yau
2. Modelling in Machine Learning by Christopher Yau
3. Bayesian Deep Learning by tbc
4. Approximate Inference by Kaspar Märtens
5. Differentiable Programming by Dominic Danks
6. Health applications of Bayesian ML by tbc
7. Bayesian Causal Inference by tbc
8. Reading Week: Student-led Presentations
9. Guest Lecture by tbc
The following resources maybe helpful pre-reading to familiarise yourself with background mathematical concepts and introductory material on Bayesian Statistics:
Probabilistic machine learning and artificial intelligence by Zoubin Ghahramani
Mathematics for Machine Learning by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong.
Pattern Recognition and Machine Learning by Chris Bishop