Deep Learning Research

Module overview

Deep learning has revolutionised numerous fields in recent years. We've witnessed improvements in everything from computer vision through speech analysis to natural language processing. This module focuses on the latest advances in deep learning and will allow you to start to understand, implement, and critically appraise recently published research, as well as give you some of the wider context of research in the field. As part of this module, you will have the opportunity to extend on the latest research, contributing with your own ideas, critical thinking, and experimental design skills. Due to the active and effervescent nature of the field, deep learning almost equates to research. Our objective is to equip you with the knowledge and skills required to engage with research as it emerges -- to be able to distinguish high-quality work that will change the course of the field from simple buzz. In this process, we will teach you how to build your own scientifically sound experiments and how to identify contributions you can make that would be valuable for the deep learning community.

Aims and Objectives

Learning Outcomes

Subject Specific Practical Skills

Having successfully completed this module you will be able to:

Use data visualisation tools to effectively communicate empirical findings
Use high-performance computational clusters to train and evaluate deep learning models
Work with deep learning libraries in order to implement state-of-the-art experiments

Knowledge and Understanding

Having successfully completed this module, you will be able to demonstrate knowledge and understanding of:

Key challenges to quantifying deep models' performance in the wild and the main approaches towards achieving trustworthy performance
The technical underpinnings of state-of-the-art deep learning models, approaches and analysis of learned representations
The main perspectives used to interpret and reason about representation learning and related phenomena

Subject Specific Intellectual and Research Skills

Having successfully completed this module you will be able to:

Critically appraise experimental design
Propose improvements and extensions to existing experimental designs from recent papers
Critically appraise recent scientific literature in various specialised subfields of deep learning

Learning and Teaching

Teaching and learning methods

Lectures, discussion seminars, group research projects, and guided self-study

Study time
Type	Hours
Seminar	12
Project supervision	12
Completion of assessment task	75
Lecture	24
Wider reading or practice	27
Total study time	150

Resources & Reading list

Textbooks

Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016). Deep Learning.

Assessment

Summative

This is how we’ll formally assess what you have learned in this module.

Breakdown
Method	Percentage contribution
A lab report	30%
Analysis and report	30%
Group project report	40%

Referral

This is how we’ll assess you if you don’t meet the criteria to pass this module.

Breakdown
Method	Percentage contribution
Experiment and Report	100%

Repeat

An internal repeat is where you take all of your modules again, including any you passed. An external repeat is where you only re-take the modules you failed.

Breakdown
Method	Percentage contribution
Experiment and Report	100%

Repeat Information

Repeat type: Internal & External