Keele Badge

CSC-20071 - Module Specification
School of Computer Science and Mathematics
Faculty of Natural Sciences

For academic year: 2025/26 Last Updated: 04 December 2025

CSC-20071 - Applied Deep Learning
Coordinator: Baidaa Al-Bander
Lecture Time: See Timetable...
Level: Level 5
Credits: 15
Study Hours: 150
School Office: 01782 733075

Programme/Approved Electives for 2025/26

None

Available as a Free Standing Elective

No

Co-requisites

None

Prerequisites

CSC-10058 Introduction to Data Science I
CSC-10060 Introduction to Data Science II
MAT-10055 Mathematical Techniques for Data Science

Barred Combinations

None

Description for 2025/26

This module will provide students with an introduction to applied deep learning, with a focus on understanding its capabilities and writing programs that use appropriate software libraries to apply deep learning to tasks such as text analysis, computer vision, image processing and pattern recognition.

Aims
The aim of the module is to provide students with an introduction to deep learning, with a focus on understanding its capabilities and writing programs that use a software library to apply deep learning to tasks such as pattern recognition and classification when applied to text processing, computer vision and image processing.

Intended Learning Outcomes

Identify and describe the capabilities and limitations of deep neural networks, including convolutional neural networks and long short term memory networks: Develop software that uses appropriate libraries to create, train and evaluate deep neural networks: Apply deep learning to tasks such as computer vision and textual sentiment analysis using techniques such as transfer learning:

Study hours

14 hours lectures
24 hours practical classes
22 hours coursework preparation
90 hours private study

School Rules

CSC-20043 Computational and Artificial Intelligence 1

Description of Module Assessment

1: Assignment weighted 100%
Deep learning software development and recorded screencast
Assignment and Demo: This assessment is designed to evaluate your proficiency in applying deep learning techniques to diverse data modalities (image and text) and tasks. It emphasises: 1.Preprocessing and preparation of datasets to suit specific tasks, 2.Model development, training, and hyperparameter tuning for performance improvement, 3.Performance evaluation and interpretation using appropriate metrics, 4.Clear visualisation of results for insightful analysis, 5.Applying advanced techniques such as transfer learning, regularisation, and data augmentation, 6.Practical application of segmentation techniques in the medical domain, 7.Effective communication and demonstration of project outcomes through a video presentation for 15 minutes. Programme code (equivalent to a 3000-word report) together with a "recorded screencast" (equivalent to a 2000-word report).

The University undertakes a continuous review of its teaching and research provision to ensure programmes are of a high quality and changes may be made to modules where it is necessary and reasonable to do so. Please be aware that minor changes to modules, such as a change to an individual assessment, can occur up until enrolment, although we endeavour to give you as much notice as possible of any changes. Details about the circumstance in which changes are made to programmes can be found in the Student Agreement, available at: https://www.keele.ac.uk/legalgovernancecompliance/governance/actcharterstatutesordinancesandregulations/studenttermsconditions/

Last Updated: 04 December 2025