# COMPGI09 - Applied Machine Learning

**This database contains 2016-17 versions of the syllabuses.** For current versions please see here.

Code | COMPGI09 |
---|---|

Year | MSc |

Prerequisites | Students should have a good command of basic mathematics including linear algebra, multivariate calculus and probability to first year undergraduate mathematics level. Students are expected to be familiar with basic machine learning concepts and will ideally have taken Supervised Learning and Graphical Models in Term 1 (or the Gatsby modules). Students are expected to be able to be competent in writing computer code, for example Python. |

Term | 2 |

Taught By | David Barber (100%) |

Aims | Applied Machine Learning aims to cover some of the issues that may arise in the practical application of machine learning in real-world problems. In addition, the course will cover some of the mathematics and techniques behind basic data analysis methods for both static and time-series data. |

Learning Outcomes | The ability to: assess the effectiveness of solutions presented and to question them in an intelligent way; synthesise solutions to general open-ended problems covering material from the whole programme, tempered with information on commercial reality obtained from this course. |

# Content:

We will cover both large scale linear and non-linear (deep learning) aspects, discussing issues related to optimisation and scalability.

A key aspect of the module is that coursework is related to competing in online machine learning competitions (Kaggle) in small teams, with the associated mark related to how well the team does compared to the global leaderboard. Students are expected to self-learn any computational techniques that might be useful for solving such real world problems. From experience, Python and the associated libraries such as Theano and Skikitlearn have proved useful for students in applying their knowledge to solving Kaggle challenges.

# Method of Instruction:

Lecture presentations with associated class problems.

# Assessment:

The course has the following assessment components:

- Written Examination (2.5 hours, 50%)
- Coursework Section. The coursework is based on assessed practical challenges hosted by Kaggle (50%).

To pass this course, students must:

- Obtain an overall pass mark of 50% for all sections combined
- Obtain a minimum mark of 50% in each component.

# Resources:

To be notified as the course progresses, according to the business themes covered.