STAT40970 Machine Learning & AI (online)

Academic Year 2024/2025

Machine learning makes predictions from data with a focus on algorithmic efficiency and optimization with respect to prediction accuracy. Following on from STAT30270/STAT40750, this module explores crucial topics in machine learning within the context of artificial intelligence, including neural networks, deep learning, big data applications, benchmarking of prediction methods. The overarching objective is to demonstrate the utilization of algorithms capable of learning and making predictions from complex data, including self-tuning and adaptation to diverse data structures. While these methods often pose challenges in interpretation and inherently exhibit a black-box nature, the module explores important considerations in their construction, use, interpretation, and comparison. Implementation of these machine learning methods is covered using the statistical software R and the Keras library, providing a hands-on approach to reinforce theoretical concepts.

Show/hide contentOpenClose All

Curricular information is subject to change

Learning Outcomes:

On completion of this module, students should have acquired the following skills:
- Have an understanding of the theory regarding all the machine learning and artificial intelligence methods introduced.
- Being able to apply a range of machine learning and artificial intelligence methods, including deep learning.
- Being able to tune and evaluate the performance of the methods introduced, benchmarking them against each other based on out-of-sample prediction performance.
- Use the statistical software R and the keras library to implement these methods.

Student Effort Hours: 
Student Effort Type Hours
Specified Learning Activities

25
Autonomous Student Learning

60
Online Learning

35
Total

120
Approaches to Teaching and Learning:
Video lectures posted each week that walk through module content, blending theory with examples and applications.
Practice problem and coding-based problem sheets to enable self-assessment of learning outcomes.
All content delivered using the VLE, which includes a monitored discussion forum with topics created for each weeks lecture material. 
Requirements, Exclusions and Recommendations
Learning Requirements:

- Knowledge and understanding of statistical machine learning theory and methods for supervised learning and classification, at a level equivalent to that which would be achieved upon completion of "STAT30270 Statistical Machine Learning" (or STAT40750), or modules with similar contents and learning outcomes.
- Knowledge of data programming and data analysis at a level equivalent to that which would be achieved upon completion of "STAT30340 Data Programming with R", and modules with a relevant component of coding and implementation of statistical methods with R.
- Knowledge of linear algebra (vectors, vector spaces, matrices), calculus (derivatives), and function optimization.
- Knowledge of regression analysis and linear models, including multiple linear regression.
- Understanding of statistical inference (confidence intervals, hypothesis testing, etc.) and familiarity with standard probability distributions (Gaussian, binomial, etc.).

Learning Recommendations:

- Knowledge and understanding of basic Bayesian inference would be beneficial.


Module Requisites and Incompatibles
Not applicable to this module.
 
Assessment Strategy  
Description Timing Open Book Exam Component Scale Must Pass Component % of Final Grade
Exam (Online): Online end of term exam. n/a Alternative linear conversion grade scale 40% No

70
Assignment(Including Essay): The assignment may include a mix of exercises, questions, code-based exercises, data analysis tasks. n/a Other No

15

Carry forward of passed components
No
 
Resit In Terminal Exam
Summer Yes - 2 Hour
Please see Student Jargon Buster for more information about remediation types and timing. 
Feedback Strategy/Strategies

• Feedback individually to students, post-assessment

How will my Feedback be Delivered?

Not yet recorded.

Goodfellow, Bengio, Courville - Deep Learning - https://www.deeplearningbook.org/

Murphy - Probabilistic Machine Learning: An Introduction – https://probml.github.io/pml-book/book1.html

Hastie, Tibshirani, Friedman - The Elements of Statistical Learning - https://hastie.su.domains/ElemStatLearn/

Bishop - Pattern Recognition and Machine Learning - https://www.microsoft.com/en-us/research/publication/pattern-recognition-machine-learning/