Durham University
Programme and Module Handbook

Postgraduate Programme and Module Handbook 2020-2021 (archived)

Module MATH42815: Machine Learning

Department: Mathematical Sciences

MATH42815: Machine Learning

Type Tied Level 4 Credits 15 Availability Available in 2020/21 Module Cap None.
Tied to G5K823
Tied to G5K923

Prerequisites

  • None

Corequisites

  • None

Excluded Combination of Modules

  • None

Aims

  • To introduce the essential knowledge and skills required in machine learning for data science.

Content

  • Feature selection and regularization for big data (e.g. ridge and lasso regression).
  • Flexible methods for fitting curves to data (e.g. polynomial regression and splines).
  • Supervised machine learning (e.g. decision/classification trees, support vector machines, neural networks, deep learning).

Learning Outcomes

Subject-specific Knowledge:
  • By the end of the module students will:
  • be aware of a wide range of supervised learning methods.
  • have a systematic and coherent understanding of the theory, computation and application of the topics studied.
  • have acquired a coherent body of applicable knowledge on modern regression methods, decision-based machine-learning techniques, support vector machines, neural networks, and deep learning.
Subject-specific Skills:
  • In addition, students will have acquired:
  • programming skills generally used in machine learning.
  • Ability to identify and apply appropriate supervised learning methods to modern real-world problems.
Key Skills:
  • Students will have skills in the following areas: synthesis of data and data analysis, critical and analytical thinking, statistical modelling, computer skills.

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

  • This module will be delivered by the Department of Mathematical Sciences.
  • Workshops describe theory and its application to concrete examples, concretize understanding via the application of calculational and computational methods to more complex problems, as well as providing feedback and encouraging active engagement via discussion and groupwork.
  • Online resources support learning and normally include: video content, directed reading, reflection through activities, opportunities for self-assessment, and peer-to-peer learning within a tutor-facilitated discussion board.
  • Surgeries give students the chance to pose personalized questions on both theory and practice.
  • Summative assignments are designed to test the acquisition and articulation of knowledge and critical understanding, and skills of implementation and interpretation of calculational and computational methods as applied to both synthetic and real problems.

Teaching Methods and Learning Hours

Activity Number Frequency Duration Total/Hours
Workshops (a combination of live lectures, computer practicals, problem classes, and tutorials) 12 3 times per week (Term 2, weeks 11-14) 2 hours 24
Lectures 8 2 times per week (Term 2, weeks 11-14) 1 hour 8
Surgeries 12 3 times per week (Term 2, weeks 11-14) 1 hour 12
Preparation, exercises, and reading 106
Total 150

Summative Assessment

Component: Coursework Component Weighting: 25%
Element Length / duration Element Weighting Resit Opportunity
Quizzes (e-assessments) 100%
Component: Assignment 1 Component Weighting: 25%
Element Length / duration Element Weighting Resit Opportunity
Assignment 100%
Component: Assignment 2 Component Weighting: 50%
Element Length / duration Element Weighting Resit Opportunity
Assignment 100%

Formative Assessment:

None


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