Skip to main content

Unit information: Applied Deep Learning (Teaching Unit) in 2020/21

Unit name Applied Deep Learning (Teaching Unit)
Unit code COMSM0045
Credit points 0
Level of study M/7
Teaching block(s) Teaching Block 1 (weeks 1 - 12)
Unit director Dr. Damen
Open unit status Not open
Pre-requisites

COMSM30035 Machine Learning (Teaching Unit) or equivalent.

Co-requisites

EITHER Assessment Units COMSM0043 Applied Deep Learning (Exam assessment, 10 credits)

OR COMSM0044 Applied Deep Learning (Coursework assessment, 15 credits).

Please note:

COMSM0046 is the Teaching Unit for the Applied Deep Learning option.

Single Honours Computer Science students can choose to be assessed by either examination (10 credits, COMSM0043) or coursework (15 credits, COMSM0044) by selecting the appropriate co-requisite assessment unit.

Any other students that are permitted to take the Applied Deep Learning option are assessed by examination (10 credits) and should be enrolled on the co-requisite exam assessment unit (COMSM0043).

School/department Department of Computer Science
Faculty Faculty of Engineering

Description

The unit introduces the students to the latest deep architectures,as well as learning approaches to optimising these for a variety of classification andregression problems. The unit paves the path from understanding the fundamentals of convolutional and recurrent neural networks through to trainingand optimisation as well as evaluation of learnt outcomes. The unit’s approach is hands-on, focusing on the ‘how-to’ while covering the basic theoretical foundations.

Intended learning outcomes

On successful completion of this unit, students will be able to:

  1. Identify the opportunities and challenges that deep architectures, both convolutional and recurrent, bring to machine learning tasks such as classification and regression.
  2. Understand and discuss the role of a variety of optimization approaches in parameter training for deep architectures.
  3. Setup, train and evaluate deep architectures on public datasets.
  4. Replicate published experiments and discuss the successes and failures of current architectures.

When assessed by Examination, theoretical understanding gained from lectures and practical labs will be assessed in a written exam.

When assessed by Coursework, practical understanding from lectures and lab will be assessed by a coursework of replicating a published paper and a report written in groups of 2-3 students.

Teaching details

Teaching will be delivered through a combination of synchronous and asynchronous sessions, including lectures, group work, practical activities supported by drop-in sessions and self-directed exercises.

Teaching will take place over Weeks 1-7, with coursework support in weeks 8-10 and for students assessed by examination, consolidation and revision sessions in Weeks 11 and 12.

Assessment Details

Examination details:

January timed assessment (100%, 10 credits)

OR

Coursework details:

Coursework (100%) to be completed in weeks 8-10.

Reading and References

The unit will use a main textbook as well as a number of online resources. The textbook will be:

  • Goodfellow et al Deep Learning (MIT Press, 2016) ISBN: 978-0262035613

Feedback