COM3031 | 2025/6 | University of Exeter

MODULE TITLE	Probabilistic Machine Learning	CREDIT VALUE	15
MODULE CODE	COM3031	MODULE CONVENER	Dr Zeyu Fu (Coordinator)

DURATION: TERM	1	2	3
DURATION: WEEKS		12

Number of Students Taking Module (anticipated)	30

DESCRIPTION - summary of the module content

This module provides an advanced exploration of machine learning and artificial intelligence, focusing on probabilistic modeling, inference techniques, and structured learning methods. It also examines key theoretical foundations alongside advanced techniques, such as Bayesian Neural Networks and Autoencoders, which enable uncertainty quantification and probabilistic generative modeling.. The module delves into Bayesian theory, its role in handling uncertainty, and its connections to approximate inference methods and information theory. Students will also explore techniques for modeling temporally and spatially structured data, including Hidden Markov Models. Additionally, the module introduces reinforcement learning. By integrating probabilistic reasoning, approximate inference, and structured learning, this module equips students with the theoretical depth and practical skills required for tackling complex machine learning problems.

AIMS - intentions of the module

This module aims to deepen your theoretical understanding of machine learning methods while introducing advanced techniques for structured data and reinforcement learning. It builds on your existing knowledge, enhancing your analytical skills and equipping you with the ability to apply probabilistic modeling, inference methods, and AI paradigms to real-world problems. By the end of the module, you will have a comprehensive foundation in both established and emerging machine learning approaches, enabling you to critically assess and implement advanced AI techniques.

INTENDED LEARNING OUTCOMES (ILOs) (see assessment section below for how ILOs will be assessed)

On successful completion of this module you should be able to:

Module Specific Skills and Knowledge

1. Demonstrate the theoretical foundations of machine learning and AI methods;

2. Choose appropriate analysis methods for new problems;

3. Understand the principles underlying different machine learning and AI techniques;

4. Understand principles of machine learning and AI for spatially and temporally connected models;

5. Understand the principles and practice of reinforcement learning systems.

Discipline Specific Skills and Knowledge

6. Describe and compare different theoretical approaches to a single problem;

7. Learn a variety machine learning and AI methods and apply them to real problems.

Personal and Key Transferable / Employment Skills and Knowledge

8. Plan and write a technical report;

9. Adapt existing technical knowledge to learning new methods.

SYLLABUS PLAN - summary of the structure and academic content of the module

Indicative syllabus plan; precise content may vary from year to year.

• Bayesian methods: theoretical perspectives; conjugate families; Monte Carlo sampling methods; approximations including Laplace approximations, variational approximation, expectation propagation.

• Bayesian Neural Networks and Autoencoders: Bayesian Neural Networks for uncertainty estimation; Autoencoders and their applications.

• Information theory: information, entropy; coding; learning from an information theoretic point of view.

• Learning in spatially and temporally connected models: Hidden Markov models.

• Reinforcement learning: Multi-armed bandits; finite Markov decision processes; temporal difference learning; on and off policy learning.

LEARNING AND TEACHING

LEARNING ACTIVITIES AND TEACHING METHODS (given in hours of study time)

Scheduled Learning & Teaching Activities	35	Guided Independent Study	115	Placement / Study Abroad	0

DETAILS OF LEARNING ACTIVITIES AND TEACHING METHODS

Category	Hours of study time	Description
Scheduled Learning and Teaching activities	20	Lectures
Scheduled Learning and Teaching activities	15	Workshops and tutorials
Guided Independent Study	115	Coursework, private study, reading

ASSESSMENT

FORMATIVE ASSESSMENT - for feedback and development purposes; does not count towards module grade

SUMMATIVE ASSESSMENT (% of credit)

Coursework	30	Written Exams	70	Practical Exams	0

DETAILS OF SUMMATIVE ASSESSMENT

Form of Assessment	% of Credit	Size of Assessment (e.g. duration/length)	ILOs Assessed	Feedback Method
Written exam – closed book	70	2 hours (Summer)	1-6	Orally on request
Coursework	30	30 hours	1-4, 6-9	Written

DETAILS OF RE-ASSESSMENT (where required by referral or deferral)

Original Form of Assessment	Form of Re-assessment	ILOs Re-assessed	Time Scale for Re-assessment
Written exam – closed book	Written exam – closed book (2 hours, 70%)	1-6	Referral/deferral period
Coursework	Coursework (30 hours, 30%)	1-4, 6-9	Referral/deferral period

RE-ASSESSMENT NOTES

Reassessment will be by coursework and/or written exam in the failed or deferred element only. For referred candidates, the module mark will be capped at 40%. For deferred candidates, the module mark will be uncapped.

RESOURCES

INDICATIVE LEARNING RESOURCES - The following list is offered as an indication of the type & level of
information that you are expected to consult. Further guidance will be provided by the Module Convener

Basic reading:

ELE

Web based and Electronic Resources:

Other Resources:

Reading list for this module:

Type	Author	Title	Edition	Publisher	Year	ISBN
Set	Christopher Bishop	Pattern Recognition and Machine Learning		Springer	2007	978-0387310732
Set	Russell, S. and Norvig, P.	Artificial Intelligence: A Modern Approach	4	Pearson	2016	978-1292153964
Set	Mackay, D.J.C.	Information Theory, Inference, and Learning	1	Cambridge	2006	978-0521642989
Set	Hastie, T., Tibshirani, R., and Friedman, J.	The Elements of Statistical Learning: Data Mining, Inference, and Prediction	2	Springer	2017	978-0387848570
Set	Sutton, R.S., Barto, A. and Bach, F.	Reinforcement Learning: An Introduction	2	MIT Press	2018	978-0262039246

CREDIT VALUE	15	ECTS VALUE	7.5

PRE-REQUISITE MODULES	MTH2006, COM2011
CO-REQUISITE MODULES

NQF LEVEL (FHEQ)	6	AVAILABLE AS DISTANCE LEARNING	No
ORIGIN DATE	Monday 10th March 2025	LAST REVISION DATE	Monday 10th March 2025

KEY WORDS SEARCH	None Defined

Probabilistic Machine Learning - 2025 entry