Module Details for the Academic Year 2018/2019

COMP40260 Connectionism

The theory and practice of modeling with artificial neural networks will be presented. Models are closely related to human cognitive processes in general and to developmental processes and learning in particular. We will also cover basic concepts from dynamical systems theory and see how these are applied in modelling human behavior.

Show/hide contentOpenClose All

On completing this module, students will have acquired the following knowledge: 1) Understanding of the foundations of connectionism and artificial neural networks; 2) Understanding of the problem area in which neural networks have usefully been applied; 3) Understanding of the opportunities and limitations of connectionist simulation of human cognitive abilities, with a special focus on human development, and, 4) Understanding of the relationship between models and data with specific focus on connectionist models, and will be able to do the following: 5) Design and apply simple neural networks using one of several customized software packages, 6) Analyze the perfromance of a network during and after training, and 7) Relate network performance to the specific details of an empirical problem. 
Item Workload
Lectures

24

Computer Aided Lab

24

Specified Learning Activities

14

Autonomous Student Learning

88

Total

150

Description % of Final Grade Timing
Continuous Assessment: Several small written exercises

75

Varies over the Semester
Essay: Brief essay (2000 words)

25

Coursework (End of Semester)

Compensation

This module is not passable by compensation

Resit Opportunities

In-semester assessment

Remediation

If you fail this module you may resit, repeat or substitute where permissible

Module Requisites and Incompatibles

Equivalent Modules

Prior Learning

Recommended:
Familiarity with elementary statistics, including distributions and the theories of linear correlation and regression will be assumed.
Curricular information is subject to change