AI Systems Implementation - COMP5850

Looking for a different module?

Module delivery information

Location Term Level1 Credits (ECTS)2 Current Convenor3 2024 to 2025
Canterbury
Spring Term 5 15 (7.5) Matteo Migliavacca checkmark-circle

Overview

Students are presented during lectures with advanced Artificial Intelligence/Machine Learning techniques (such as GAs, SVM, deep learning ,Q-Learning/Deep Q-learning, Ensembles, stochastic gradient decent, neuroevolution), including aspects of implementation, hyper parameter tuning, scalability and parallelism.
Lectures will be complemented by weekly classes, where students can consolidate their learning and apply these techniques in practice to solve small-scale problems. Learning will be evaluated by means of practical exercises and tests.
The new material, together with the material in COMP3590 and COMP5560, would form the basis for the implementation of an AI project, where students would apply these techniques to a medium-scale practical problem.

Details

Contact hours

Contact hours: 31
Private study hours: 119
Total hours: 150

Method of assessment

100% coursework

Indicative reading

• Patrick D. Smith, "Hands-On Artificial Intelligence for Beginners: An introduction to AI concepts, algorithms, and their implementation", Packt Publishing, 2018
• M. Tim Jones, "Artificial Intelligence: A Systems Approach", Jones & Bartlett Learning, 2015
• Aurélien Géron, “Hands-on Machine Learning with Scikit-Learn and TensorFlow”, O'Reilly, 2017
• Sebastian Raschka, “Python Machine Learning”, 2nd Ed, Packt Publishing, 2017
• Sarah Guido, Andreas C. Müller, “Introduction to Machine Learning with Python”, O'Reilly, 2016
• Tom Mitchell, “Machine Learning”, McGraw Hill, 1997

Learning outcomes

On successfully completing the module students will be able to:
1. Understand the techniques used to implement AI Systems, and their underpinning principles;
2. Evaluate alternative AI approaches including quality/cost trade-offs;
3. Apply AI techniques to solve realistic and real-world problems, using appropriate programming languages and libraries (e.g., Python and Scikit-Learn);
4. Analyse obtained results in terms of quality/cost and devise strategies to improve them.

Notes

  1. Credit level 5. Intermediate level module usually taken in Stage 2 of an undergraduate degree.
  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.