COMP0088 Introduction to Machine Learning

This database contains the 2018-19 versions of syllabuses. These are still being finalised and changes may occur before the start of the session.

Syllabuses from the 2017-18 session are available here.

Academic session

2018-19

Module

Introduction to Machine Learning

Code

COMP0088

Module delivery

1819/A7P/T1/COMP0088 Postgraduate

Related deliveries

None

Prior deliveries

COMPGI21

Level

Postgraduate

FHEQ Level

L7

FHEQ credits

15

Term/s

Term 1

Module leader

Kokkinos, Iason

Contributors

Kokkinos, Iason

Module administrator

Adi, Abena

Aims

To have a full understanding of the learning outcomes.

Learning outcomes

On successful completion of the module, a student will be able to:

  1. understand machine learning at both the theoretical and practical level.
  2. solve real-world machine learning problems using the right tools.

Availability and prerequisites

This module delivery is available for selection on the below-listed programmes. The relevant programme structure will specify whether the module is core, optional, or elective.

In order to be eligible to select this module as optional or elective, where available, students must meet all prerequisite conditions to the satisfaction of the module leader. Places for students taking the module as optional or elective are limited and will be allocated according to the department’s module selection policy.

Programmes on which available:

  • MRes Computational Statistics and Machine Learning
  • MSc Business Analytics (with specialisation in Computer Science)
  • MSc Computer Graphics, Vision and Imaging
  • MSc Data Science (International)
  • MSc Data Science and Machine Learning
  • MSc Data Science

Prerequisites:

There are no formal prerequisites. It is however highly recommended that students who select this module have competency in linear algebra, calculus, probability theory, and programming.

Content

Introduction to Supervised Learning

  • Linear models for regression and classification: least squares, logistic regression
  • Concepts of overfitting and regularization, L1 and L2 regularisation
  • Boosting, Decision Trees, Random Forests
  • Support Vector Machines
  • Deep Learning: Neural Networks for regression and classification, Recurrent Neural Networks

Introduction to Unsupervised Learning

  • K-means, Principal Components Analysis, Sparse Coding
  • Expectation-Maximization, Mixture of Gaussians, Factor Analysis
  • Deep Autoencoders, Generative Adversarial Networks

An indicative reading list is available via http://readinglists.ucl.ac.uk/departments/comps_eng.html.

Delivery

The module is delivered through a combination of lectures and programming exercises.

Assessment

This module delivery is assessed as below:

#

Title

Weight (%)

Notes

1

Written examination (2hrs 30mins)

70

 

2

Coursework 1

12

 

3

Coursework 2

18

 

In order to pass this module delivery, students must achieve an overall weighted module mark of 50%.