- Student Records
Programme & Unit Catalogues

CM50268: Bayesian machine learning

[Page last updated: 10 August 2020]

Follow this link for further information on academic years Academic Year: 2020/1
Further information on owning departmentsOwning Department/School: Department of Computer Science
Further information on credits Credits: 6      [equivalent to 12 CATS credits]
Further information on notional study hours Notional Study Hours: 120
Further information on unit levels Level: Masters UG & PG (FHEQ level 7)
Further information on teaching periods Period:
Semester 2
Further information on unit assessment Assessment Summary: CW 100%
Further information on supplementary assessment Supplementary Assessment:
Like-for-like reassessment (where allowed by programme regulations)
Further information on requisites Requisites:
Description: Aims:
To convey an appreciation of the philosophy and practical features of Bayesian inference, its general relevance in data science, along with key algorithms and methods of implementation in both a generic and a machine learning context.

Learning Outcomes:
After completion of the unit, students should be able to:
* explain the philosophical foundations of Bayesian inference, and critically review the advantages and disadvantages of the paradigm,
* apply and quantitatively assess approximation methods for Bayesian inference,
* critically evaluate a range of Bayesian modelling techniques within machine learning scenarios,
* implement a baseline Bayesian model (e.g. linear regression) in a relevant programming language (e.g. Python),
* employ more advanced Bayesian software libraries to solve problems in data science.

Intellectual skills:
* Conceptual understanding of Bayesian inference (T,F,A)
* Critical appreciation of probabilistic modelling paradigms (T,F,A)
Practical skills:
* Programming Bayesian analytic algorithms (T,F,A)
* Use of software packages for Bayesian modelling (T,F,A)
Transferable skills:
* Numerical programming (F,A)
* Technical report writing (F,A)

Topics covered by this unit will typically include the history and philosophy of Bayesian inference, key concepts such as priors, marginalisation and Occam's razor, practical Bayesian methodology in machine learning contexts and elsewhere, stochastic and deterministic approximation methods, specific Bayesian treatments of linear models, neural networks and Gaussian processes etc.
Further information on programme availabilityProgramme availability:

CM50268 is Optional on the following programmes:

Department of Computer Science
  • RSCM-AFM51 : Integrated PhD Accountable, Responsible and Transparent Artificial Intelligence
  • TSCM-AFM51 : MRes Accountable, Responsible and Transparent Artificial Intelligence
  • TSCM-AFM52 : MSc Accountable, Responsible and Transparent Artificial Intelligence
  • TSCM-AFM45 : MSc Data Science
  • TSCM-AWM45 : MSc Data Science
  • TSCM-AFM48 : MSc Machine Learning and Autonomous Systems
  • TSCM-AWM48 : MSc Machine Learning and Autonomous Systems