Deep Learning - COMP8685

Looking for a different module?

Module delivery information

Location Term Level1 Credits (ECTS)2 Current Convenor3 2022 to 2023
Canterbury
Spring Term 7 15 (7.5) checkmark-circle

Overview

This module looks into the training of modern deep neural networks: backpropagation, regularisation, automatic differentiation, computational graphs. Introduces different types of deep neural networks, such as, LSTM, convolutional networks, and autoencoders. Presents the theoretical underpinnings of deep learning and its mechanisms. Delves into selected recent advanced topics in deep learning. Examines applications of deep learning.

Details

Contact hours

Private Study Hours: 124
Contact Hours: 26
Total Hours: 150

Method of assessment

This module will be assessed by 100% coursework.
25% Practical assignment 1 (individual/group; approximately 20 hours)
25% Time limited assessment 1 (individual; 1 hour with 10 hours revision)
25% Practical assignment 2 (individual/group; approximately 20 hours)
25% Time limited assessment 2 (individual; 1 hour with 10 hours revision)

Indicative reading

Bengio, Yoshua, Ian Goodfellow, and Aaron Courville. Deep learning. MIT press, 2017.
Kelleher, John D. Deep learning. MIT press, 2019.
Sejnowski, Terrence J. The deep learning revolution. MIT press, 2018.

Learning outcomes

1. Comprehend the benefits of data re-representation in deep neural networks, and their ensuing modelling capacity.
2. Demonstrate an understanding of the algorithms that are required to train deep neural networks.
3. Demonstrate an awareness of computational and practical challenges existing in deep learning.
4. Demonstrate a systematic understanding of the key parameters in a neural network's architecture.
5. Competently use deep learning software to solve practical problems.
6. Understand the objectives of explainability and interpretability of neural networks.
7. Explain the differences between the major deep learning architectures.
8. Evaluate the strengths and weaknesses of the state of the art deep learning models and algorithms.

Notes

  1. Credit level 7. Undergraduate or postgraduate masters level module.
  2. ECTS credits are recognised throughout the EU and allow you to transfer credit easily from one university to another.
  3. The named convenor is the convenor for the current academic session.
Back to top

University of Kent makes every effort to ensure that module information is accurate for the relevant academic session and to provide educational services as described. However, courses, services and other matters may be subject to change. Please read our full disclaimer.