Applied Machine Learning

Course aim

This course covers 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.

Course content

Both large scale linear and non-linear (deep learning) aspects, discussing issues related to optimisation and scalability.

A key aspect of the course 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.

Textbook(s)

Nil

Prerequisite(s)

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.

Corequisite(s)

Nil

Teaching method

Note: These components may or may not be scheduled in every study period. Please refer to the timetable for further details.

Assessment

Continuous assessment, Examination

Fees

EFTSL*: 0.125
Commonwealth Supported program (Band 2)
To determine the fee for this course as part of a Commonwealth Supported program, go to:
How to determine your Commonwealth Supported course fee. (Opens new window)

Fee-paying program for domestic and international students
International students and students undertaking this course as part of a postgraduate fee paying program must refer to the relevant program home page to determine the cost for undertaking this course.

Non-award enrolment
Non-award tuition fees are set by the university. To determine the cost of this course, go to:
How to determine the relevant non award tuition fee. (Opens new window)

Not all courses are available on all of the above bases, and students must check to ensure that they are permitted to enrol in a particular course.

* Equivalent Full Time Study Load. Please note: all EFTSL values are published and calculated at ten decimal places. Values are displayed to three decimal places for ease of interpretation.