Deep Learning

Module aims

This module addresses the fundamental concepts and advanced methodologies of deep learning and relates them to real-world problems in a variety of domains. The aim is to provide an overview of different approaches, both classical and emerging. The module will equip you with the necessary knowledge and skills to work in the field of deep learning and to contribute to ongoing research in the area.

Learning outcomes

Upon successful completion of this module you will be able to:

  • express the underlying theoretical concepts of modern deep learning methods
  • compare, characterise and quantitively evaluate various deep learning approaches
  • evaluate the limitations of deep learning
  • apply deep learning techniques to real-world problems in computer vision, speech, text analysis, and graph processing


           

Module syllabus

  • Supervised vs unsupervised learning, generalisation, overfitting
  • Perceptrons, including deep vs shallow models
  • Stochastic gradient descent and backpropagation
  • Convolutional neural networks (CNN) and underlying mathematical principles
  • CNN architectures and applications in image analysis
  • Recurrent neural networks (RNN), long-short term memory (LSTM), gated recurrent units (GRU)
  • Applications on RNNs in speech analysis and machine translation
  • Mathematical principles of generative networks; variational autoencoders (VAE); generative adversarial networks (GAN)
  • Applications of generative networks in image generation
  • Graph neural networks (GNN): spectral and spatial domain methods, message passing
  • Applications of GNNs in computational social sciences, high-energy physics, and medicine

Pre-requisites

>> CO496 Mathematics for Machine Learning

Exclusions:

Year 4 - MEng Mathematics and Computer Science
Year 4 - MEng Mathematics and Computer Science (Computational Statistics)
Year 4 - MEng Mathematics and Computer Science (Pure Maths and Computational Logic)
Year 5 - M.Sc Artificial Intelligence

Teaching methods

The material will be taught through traditional lectures backed up by unassessed, formative, in-class exercises and supervised laboratory sessions. The lab sessions will be supervised, so you will receive technical support from Graduate Teaching Assistants (GTAs).

The Piazza Q&A web service will be used as an open online discussion forum for the module.    

Assessments

There will be two lab-based coursework exercises contributing a total of 50% of the marks for the module. There will be a final written exam, contributing 50% of the marks, which will test both theoretical and practical aspects of the subject.  

There will be detailed written feedback for each of the assessed courseworks and class-wide feedback explaining common pitfalls and suggestions for improvement.

Module leaders

Dr Stefanos Zafeiriou
Professor Bjoern Schuller
Professor Michael Bronstein