Module MATH31520: Machine Learning and Neural Networks

Department: Mathematical Sciences

MATH31520: Machine Learning and Neural Networks

Prerequisites

• Data Science and Statistical Computation and Statistical Inference

Corequisites

• None

Excluded Combination of Modules

• None

Aims

• To provide advanced methodological and practical knowledge in the field of machine learning, covering a wide range of the modelling and computational techniques ubiquitous in recent scientific and technological applications, and to provide an introduction to neural networks.

Content

• Function learning, loss functions, training.
• Bias-variance decomposition, overfitting.
• Regression and classification problems.
• Linear and non-linear learning.
• Model selection and cross validation.
• Shrinkage methods.
• Kernels and SVMs.
• Ensemble learning (boosting, bagging, random forests).
• Feature engineering.
• Intro to neural networks.
• Extensions: super learners.

Learning Outcomes

• By the end of the module students will:
• have a systematic and coherent understanding of the mathematical theory underlying a variety of machine learning techniques;
• have an understanding of the relationship of this theory to other statistical techniques;
• be able to make appropriate modelling and algorithmic choices for a given problem or application;
• be able to implement those choices in software, and test their validity and performance;
• have an elementary understanding of the functioning and uses of neural networks.

• Students will have mathematical skills in the following areas: modelling, optimization, computation.

• Students will have skills in the following areas: problem formulation and solution, critical and analytical thinking, computer programming.

Modes of Teaching, Learning and Assessment and how these contribute to the learning outcomes of the module

• Lectures demonstrate what is required to be learned and the application of the theory to practical examples.
• Problem classes show how to solve example problems in an ideal way, revealing also the thought processes behind such solutions.
• Computer practicals consolidate the studied material, explore theoretical ideas in practice, enhance practical understanding, and develop practical data analysis skills.
• Assignments for self-study develop problem-solving skills and enable students to test and develop their knowledge and understanding.
• Formative assessments provide feedback to guide students in the correct development of their knowledge and skills in preparation for the summative assessment.
• Computer-based examinations assess the ability to use statistical software and basic programming to solve predictable and unpredictable problems.
• The end-of-year examination assesses the knowledge acquired and the ability to solve predictable and unpredictable problems.

Teaching Methods and Learning Hours

Summative Assessment

Formative Assessment:

Eight written or electronic assignments to be assessed and returned. Other assignments are set for self-study and complete solutions are made available to students.

■ Attendance at all activities marked with this symbol will be monitored. Students who fail to attend these activities, or to complete the summative or formative assessment specified above, will be subject to the procedures defined in the University's General Regulation V, and may be required to leave the University