Mathematical and computational fundamentals of artificial neural networks and fuzzy systems, and their applications in signal andimage processing, pattern recognition and modelling. Neurocomputing topics: the perceptron and linear neural networks; multi-layer feedforward neural networks; related learning algorithms; self-organising systems, principal component analysis; competitive learning, vector quantization; self-organising feature maps and recurrent neural networks. Fuzzy system topics: fuzzy sets, arithmetic and relations; fuzzy logic, membership functions; fuzzy inference and fuzzy systems; fuzzy logic controllers and predictors; adaptive neuro-fuzzy inference systems

Neurocomputing

• Basic concepts of "neurocomputing": Artificial Neural Networks (ANN) and their biological roots and motivations. ANNs as numerical data/signal/image processing devices. Encoding (training phase) and decoding (active phase).Taxonomy of neural networks: feedforward and recurrent networks with supervised and unsupervised learning laws. Static and dynamic processing systems. Basic data structures: mapping of vector spaces, clusters, principal components.
• Basic terminology related to an artificial neuron: a summing dendrite, synapses and their weights, pre- and post-synaptic signals, activation potential and activation function. Excitatory and inhibitory synapses. The biasing input. Types of activating functions.
• The Perceptron and its learning law. Classification of linearly separable patterns.
• Linear Networks: Adaline --- the adaptive linear element. Linear regression. The Wiener-Hopf equation. The Least-Mean-Square (Widrow-Hoff) learning algorithm. Method of steepest descent. Adaline as a linear adaptive filter. A sequential regression algorithm.
• Multi-Layer Feedforward Neural Networks: aka Multi-Layer Perceptrons. Supervised Learning. Approximation and interpolation of functions. Back-Propagation Learning law. Fast training algorithms. Applications of multilayer perceptrons: Image coding, Paint-quality inspection, Nettalk.
• Radial-Basis function (RBF) networks and their application in function interpolation, approximation and modelling probability distributions.
• Self-Organising systems. Unsupervised Learning. Local learning laws. Generalised Hebbian Algorithm. The Oja's and Sanger's rules. Principal component analysis --- Karhunen-Loeve transform.
• Competitive Learning: MinNet and MaxNet networks. Clustering. Learning Vector Quantisation. Codebooks. Application in data compression.
• Self-Organising Feature Maps Kohonen networks.

Fuzzy computing

• fuzzy sets, fuzzy arithmetic and relations;
• fuzzy logic, membership functions;
• fuzzy inference and fuzzy systems;
• fuzzy logic controllers and predictors;
• fuzzy system applications in image processing and pattern recognition,

• Simon Haykin, Neural Networks -- a Comprehensive Foundation, Prentice Hall, 2nd ed., 1999, ISBN 0-13-273350-1
• Andrew P. Paplinski -- Lecture notes http://www.csse.monash.edu.au/courseware/cse5301
• H. Demuth , M. Beale, Neural Network Toolbox User's Guide. For use with MATLAB, The MathWorks Inc
• Fuzzy Logic Toolbox. For use with MATLAB. User's Guide. The MathWorks Inc
• Martin T. Hagan,. H. Demuth, M. Beale, Neural Network Design, PWS Publishing, 1996, ISBN 0-534-94332-2

60% reports and assignments + 40% final examination (2 hours)

2 hours lectures and 2 hours of practicals per week

A class of Linux/Windows XP workstations with the following packages installed:

• MATLAB with
• Neural Network Toolbox
• Fuzzy Systems Toolbox
• Image Processing Toolbox

It is a licenced software administered by CSSE TSU

Two hours a week of a supervised work and four hours a week of an unsupervised work

• Software Title:
• Vendor:
• Version:
• OS: MS Windows XP ( ) and/or LINUX ( )
• License Details: (A valid software license certificate/s or Vendor permission must be available upon request if the software is to be installed for teaching)
• Are we currently licensed: Yes ( ) or No ( ) (If unsure, please check with your local IT support )
• If (Yes), who is the contact person for this software?:
• If (No), will the software license be arranged by: Staff member requesting the software ( ) or Technical Services* ( ) ? *If the latter is selected, please discuss your requirement/s with myself ASAP, prior to finalising your request, as there could be financial or resourcing implications.
• Is the software to be installed and accessed from a: Client/Workstation ( ), or Server ( ) ?
• Type of license: Site License ( ), Freeware ( ), FOSS (Free and Open Source Software) ( ), Shareware ( ), Lab based ( ) # of Licenses needed ____
• In what week will you commence using the software in class? Semester 1 (Week ___ ) and/or Semester 2 (Week ___ ):
• Nominated Staff For Acceptance Testing Software: (Name) (Phone) (Email)
• Additional Information: Special Requirements, Software Configuration/Installation Requirements, etc:

Vendor: Mathworks Software Title: MATLAB with

MAT1811/1812 or MAT1841/1830 or equivalent, and 2 years or more of study in a computing related course.