This course is the next step beyond our introductory machine learning course and teaches students about modern techniques for machine learning with high-dimensional image and sequence (time-series) data, and the underlying computational structures for such systems.

TBC

None

None

Exam 60%, Lab Reports 16%, Written Assignment 14%, Set Exercise 10%.

The coursework cannot be redone because the feedback provided to the students after the original coursework would give any students redoing the coursework an unfair advantage.

The lab exercises cannot be redone because they need to be actively done during the lab sessions throughout the semester.

Students will be able to resit the set exercise class tests and the exam.

The aim of this course is to go beyond our introductory machine learning course, and teach students about modern techniques for machine learning with high-dimensional image and sequence (time-series) data, and the underlying computational structures for such systems. Teach the students about managing large data sets, and the engineering pipelines for large-scale machine learning tasks.  In this course, students will learn the foundations of deep learning and dynamic models for time-series analysis.

By the end of this course students will be able to:

1. Understand the major technology trends in advanced machine learning;

2. Build, train and apply fully connected deep neural networks;

3. Know how to implement efficient, vectorised neural networks in python and understand the underlying backends;

4. Apply deep learning methods to new applications;

5. Understand the machine learning pipeline, and engineering aspects of training data collation, and the importance of unlabelled data.

Students must submit at least 75% by weight of the components (including examinations or class tests) of the course's summative assessment.