Module Database Search



MODULE DESCRIPTOR
Module Title
Computational Intelligence
Reference CM4601 Version 1
Created March 2020 SCQF Level SCQF 10
Approved July 2020 SCQF Points 30
Amended ECTS Points 15

Aims of Module
To provide key concepts of adaptive intelligent systems and the design and implementation of such systems for real-world problems.

Learning Outcomes for Module
On completion of this module, students are expected to be able to:
1 Formulate and analyse problems in optimisation and machine learning and select suitable solution techniques.
2 Design and implement an adaptive intelligent system for a given application.
3 Critically appraise current application areas of adaptive intelligent systems.
4 Integrate selected computational intelligence algorithms in adaptive intelligent systems.

Indicative Module Content
Techniques: evolutionary algorithms (GA, EDA, PSO, ACO), local search, constraint satisfaction and optimisation. Applications: function optimisation, artificial life, network analysis, biology and medicine, neural networks, image analysis, engineering, evolutionary art and music and parameter tuning. Theory: exploration v exploitation, local and global optima, satisfaction and optimisation, premature convergence, plateauing and Schema Theorem. Practical: problem representations, selection, genetic operators, parameter choices, evaluation and tuning of algorithms, toolkits and real world case studies in scientific optimisation, medicine, engineering and industry.

Module Delivery
Key concepts are introduced and illustrated through the medium of lectures. These are reinforced in tutorial classes. Laboratory sessions provide a series of exercises designed to develop proficiency in techniques essential to the development of adaptive intelligent systems.

Indicative Student Workload Full Time Part Time
Contact Hours 96 N/A
Non-Contact Hours 204 N/A
Placement/Work-Based Learning Experience [Notional] Hours N/A N/A
TOTAL 300 N/A
Actual Placement hours for professional, statutory or regulatory body    

ASSESSMENT PLAN
If a major/minor model is used and box is ticked, % weightings below are indicative only.
Component 1
Type: Examination Weighting: 50% Outcomes Assessed: 1, 3
Description: Closed book Examination.
Component 2
Type: Coursework Weighting: 50% Outcomes Assessed: 2, 4
Description: Individual Coursework.

MODULE PERFORMANCE DESCRIPTOR
Explanatory Text
The calculation of the overall grade for this module is based on a 50% weighting for Component 1 (Examination) and 50% weighting for Component 2 (Coursework). An overall minimum grade D is required to pass the module.
Coursework:
Examination: A B C D E F NS
A A A B B B E
B A B B C C E
C B B C C D E
D B C C D D E
E C C D D E E
F E E E E E F
NS Non-submission of work by published deadline or non-attendance for examination

Module Requirements
Prerequisites for Module CM2601 and CM1606 or equivalents.
Corequisites for module None.
Precluded Modules None.

INDICATIVE BIBLIOGRAPHY
1 Kordon, A. 2010. Applying Computational Intelligence: How To Create Value. Springer.
2 Kacprzyk J, Pedrycz W (2015) Springer Handbook of Computational Intelligence.
3 Fogel D, Liu D, Keller J (2016) Fundamentals of Computational Intelligence: Neural Networks, Fuzzy Systems, and Evolutionary Computation.
4 Bhattacharyya, Snášel, Pan, Debashis (2019) Hybrid Computational Intelligence: Research and Applications.
5 Kumar, Raman, Wiil (2019) Recent Advances in Computational Intelligence.
6 Hemanth , Jude (2019) Human Behaviour Analysis Using Intelligent Systems.

Robert Gordon University, Garthdee House, Aberdeen, AB10 7QB, Scotland, UK: a Scottish charity, registration No. SC013781