STAT40970 Machine Learning & AI (online)

Academic Year 2021/2022

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 will explore important topics in Machine Learning in the context of Artificial Intelligence. The goal of this module is to show how to employ algorithms that can learn and make predictions from complex data, including self-tuning and adaptation to a wide variety of data structures. Although the models are often difficult to interpret and the approaches are necessarily black-box in nature, the module will explore important considerations in their construction, use, interpretation, and comparison.
Topics may include: Neural networks, Deep Learning, big data applications, benchmarking of machine learning prediction methods, topic modelling, Hidden Markov Models.
The module will cover how to implement these machine learning methods using the statistical software R and the Keras library.

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 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 Keras 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 basic statistical machine learning theory and methods for supervised learning and classification (as from STAT30270 - STAT40750).
Familiarity with the R software for statistical computing and data programming.


Module Requisites and Incompatibles
Not applicable to this module.
 
Assessment Strategy  
Description Timing Open Book Exam Component Scale Must Pass Component % of Final Grade
Continuous Assessment: Homework assignments, code-based exercises, data analysis tasks Varies over the Trimester n/a Other No

30
Examination: End of trimester written exam 2 hour End of Trimester Exam No Other No

70

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.