Evolutionary & Adaptive Computing - COM00177M

«Back to module search

Module summary

This module introduces a range of biologically-inspired approaches to computing.

Module will run

Occurrence	Teaching period
A	Semester 2 2024-25

Module aims

This module introduces a range of biologically-inspired approaches to computing. It provides a foundation of both theoretical and practical knowledge on the subject of evolutionary computation, an optimisation technique inspired by biological evolution. Students will have hands-on experience implementing a number of types of evolutionary algorithms using Python and the library DEAP: Distributed Evolutionary Algorithms in Python, to solve a range of different types of problems. The module also studies the use of Agents and Multi-agent Systems as a modelling paradigm, with a focus on evolutionary adaptation and learning.

Module learning outcomes

• Design and implement evolutionary systems to address a complex problem.
• Understand the biological underpinnings of a range of evolutionary algorithms, and use them to optimise mathematical functions and agent behaviours.
• Define a range of agent behaviours and represent them in a form that is well suited to natural selection
• Model processes in populations of agents using both hand-written and data-driven mathematical models
• Evaluate and develop the performance of evolutionary and multi agent systems, and critically and correctly evaluate their implementation.

Indicative assessment

Task	% of module mark
Essay/coursework	100

Special assessment rules

None

Indicative reassessment

Task	% of module mark
Essay/coursework	100

Module feedback

Feedback is provided through work in practical sessions, and after the final assessment as per normal University guidelines.

Indicative reading

++ Banzhaf et al, Genetic Programming: An Introduction, Morgan Kaufmann , 1999

++ M. Mitchell, An Introduction to Genetic Algorithms, MIT Press, 1998