FIT5167 - Natural computation for intelligent systems

Leader(s): Andrew Paplinski

Offered

Not offered in 2009

Synopsis

This unit looks at the development and application of biologically inspired models of computation. We study: basic components of a natural neural systems: synapses, dendrites and neurons and their computational models; fundamental concepts of data and signal encoding and processing; neural network architectures: pattern association networks, auto associative networks, feedforward networks, competitive networks, self organizing networks and recurrent networks; plasticity and learning. Hebb rule, supervised learning, reinforced learning, error-correcting learning, unsupervised learning, competitive learning, self-organization.

Objectives

At the completion of this unit students will:

1. understand basic computational principles underlying the operations of biological neural systems;
2. have knowledge of computational methods of simulating biological and artificial neural systems;
3. have knowledge of supervised, unsupervised and self-organizing neuronal learning systems;
4. be able to use computer software to simulate behaviour of neurons and neural networks.

Assessment

Assignments: 40%; Exam, department-closed book (3 hours): 60%.

Contact hours

2 hours of lectures/week; 1 hour of tutorials/week.

Prerequisites

For MAIT students, FIT9017, FIT9018, FIT9019, FIT9030, FIT9020 and FIT4037.

Prohibitions

CSE5301

Additional information on this unit is available from the faculty at:

http://www.infotech.monash.edu.au/units/fit5167