Traditional computation finds it either difficult or impossible to perform a certain key range of tasks associated with pattern recognition, problem solving and autonomous intelligence. Great progress towards designing software for such tasks has emerged by taking inspiration from a range of natural, mainly biological, systems.
The aims of this course are to:
- introduce an appreciation of the former
- introduce the main biologically-inspired algorithms and techniques which are now commonly researched and applied
- establish a practical understanding of the real-world problems to which these techniques may be fruitfully be applied.
Pre-requisite course(s): F29AI Artificial Intelligence and Intelligent Agents or equivalnt.
- classical vs. biologically-inspired computation,
- evolutionary algorithms (basic EA design, and how they are applied to a wide range of problems)
- swarm intelligence (ant colony methods, particle swarm optimisation)
- neural computation (perceptrons, multilayer perceptrons, associative networks)
- cellular automata
Learning Outcomes: Subject Mastery
Understanding, Knowledge and Cognitive Skills Scholarship, Enquiry and Research (Research-Informed Learning)
- Understanding of limitations of traditional computation.
- A critical understanding of a range of biologically inspired computation methods, their limitations and areas of applicability.
Ability to apply one or more biologically inspired techniques in solving a practical problem.
Learning Outcomes: Personal Abilities
Industrial, Commercial & Professional Practice Autonomy, Accountability & Working with Others Communication, Numeracy & ICT
- Identify and define approaches that can be used to apply bio-inspired methods to existing problems in optimisation and machine learning.
- Exercise substantial autonomy and initiative (courseworks) (PDP)
- Demonstrate critical reflection (courseworks) (PDP).
Assessment: Examination: (weighting – 50%) Coursework: (weighting – 50%)
Re-assessment: Examination: (weighting – 100%)
SCQF Level: 11.