Module 12417 (2001)

Syllabus page 2001/2002

06-12417
Nature Inspired Learning

Level M1

kxc
10 credits in Semester 2

Links | Outline | Aims | Outcomes | Prerequisites | Teaching | Assessment | Books | Detailed Syllabus


The Module Description is a strict subset of this Syllabus Page. (The University module description has not yet been checked against the School's.)

Relevant Links

See Nature Inspired Learning Web-page for course material and further useful links.


Outline

This module gives an introduction to the main learning techniques inspired by natural, physical and biological systems. Examples of such topics include: learning classifier systems, competitive and cooperative co-evolution, evolutionary games, learning through genetic programming, support vector machines, adaptive resonance theory neural networks, Boltzmann machines, interaction between learning and evolution, Baldwin effect, Lamarckian evolution, memetic algorithms, and the evolution of neural networks.


Aims

The aims of this module are to:

  • present a range of nature inspired learning techniques
  • show how these techniques can be applied to particular problems

Learning Outcomes

On successful completion of this module, the student should be able to: Assessed by:
1demonstrate a good understanding of the nature inspired learning techniques presented in the module, and the relations between them Examination
2demonstrate an understanding of the benefits and limitations of nature inspired learning algorithms Examination
3apply nature inspired learning algorithms to specific technical and scientific problems Examination

Restrictions, Prerequisites and Corequisites

Restrictions:

None

Prerequisites:

None

Co-requisites:

06-12411 (Introduction to Molecular and Quantum Computation), 06-12412 (Introduction to Neural Computation), 06-12414 (Introduction to Evolutionary Computation)


Teaching

Teaching Methods:

2 hrs/week lectures/tutorials

Contact Hours:

24


Assessment

  • Supplementary (where allowed): As the sessional assessment
  • 2 hr open book examination (100%).

Recommended Books

TitleAuthor(s)Publisher, Date
Evolutionary Computation: The Fossil RecordD.B. Fogel (Ed.)IEEE Press, 1998
Evolutionary ComputationK.A. De JongMIT Press, 2001
Neural Networks for Pattern RecognitionC.M. BishopOxford University Press, 1995
The Handbook of Brain Theory and Neural NetworksM.A. Arbib (Ed.)MIT Press, 1995
Adaptive Individuals in Evolving Populations: Models and AlgorithmsR. K. Belew & M. Mitchell (eds)Addison-Wesley, 1996

Detailed Syllabus

  1. Overview of what Nature Inspired Learning covers
  2. Learning Classifier Systems
  3. Competitive and Cooperative Co-evolution - Red Queen Effect
  4. Evolutionary Games
  5. Learning through Genetic Programming
  6. Learning from Corpus Analysis - Bootstrapping Semantic Categories
  7. Support Vector Machines
  8. Adaptive Resonance Theory Neural Networks - ART1, ART2, ART3, ARTMAP, Fuzzy ART and ARTMAP, Distributed ART and ARTMAP
  9. Boltzmann Machines
  10. Interaction between Learning and Evolution - Baldwin effect, Lamarckian evolution, memetic algorithms
  11. Evolving Neural Networks - Individual Differences, Variable Plasticity, Modularity

Last updated: 29 July 2001

Source file: /internal/modules/COMSCI/2001/xml/12417.xml

Links | Outline | Aims | Outcomes | Prerequisites | Teaching | Assessment | Books | Detailed Syllabus