ICT619 Intelligent Systems Topic 4: Artificial Neural Networks
ICT619 Intelligent Systems Topic 4: Artificial Neural Networks
ICT619 Intelligent Systems Topic 4: Artificial Neural Networks
Systems
PART B
Developing neural network applications
Design of the network
Training issues
A comparison of ANN and ES
Hybrid ANN systems
Case Studies
ICT619 2
Developing neural network
applications
ICT619 3
Software Simulations of ANN
ICT619 4
Software simulations of ANN
(cont’d)
ICT619 7
Neurocomputers
ICT619 8
Neurocomputers
ICT619 10
Neural Network Development
Methodology
ICT619 11
Neural Network Development
Methodology - the Concept Phase
Involves
Validating the proposed application
Selecting an appropriate neural paradigm.
Application validation
Problem characteristics suitable for neural network
application are:
Data intensive
Multiple interacting parameters
Incomplete, erroneous, noisy data
Solution function unknown or expensive
Requires flexibility, generalisation, fault-tolerance, speed
ICT619 12
ANN Development Methodology - the
Concept Phase (cont’d)
Common examples of applications with above
attributes are
pattern recognition (eg, printed or handwritten character,
consumer behaviour, risk patterns),
forecasting (eg, stock market), signal (audio, video, ultrasound)
processing
ICT619 16
The Design Phase (cont’d)
Connectivity
Connectivity determines the flow of signals between
neurons in the same or different layers
ICT619 17
The Design Phase (cont’d)
Feedback
There may be no feedback of output values, eg, the
multilayer perceptron
or
There may be feedback as in a recurrent network eg,
the Hopfield net
ICT619 18
The Implementation phase
Typical steps:
Gathering the training set
Selecting the development environment
Implementing the neural network
Testing and debugging the network
ICT619 19
Gathering training data (cont’d)
Collection of data
Potential sources - historical records, instrument
readings, simulation results
Preparation of data
Involves preprocessing including scaling, normalisation,
binarisation, mapping to logarithmic scale, etc.
ICT619 20
Gathering training data (cont’d)
Collection of data
Potential sources - historical records, instrument
readings, simulation results
Preparation of data
Involves preprocessing including normalisation and
possible binarisation
ICT619 22
Selecting the development
environment
ICT619 23
Selecting the development
environment
ICT619 24
Selecting the development
environment (cont’d)
ICT619 25
Implementing the neural network
ICT619 26
Implementation - Training
Overtraining
Net fails to generalise, i.e., fails to classify less than
perfect patterns
Mix of good and imperfect patterns for training helps
ICT619 28
Implementation – Training
(cont’d)
Training results may be affected by the method
of presenting data set to the network.
ICT619 29
Implementation - Testing and
Debugging
Testing can be done by:
1. Observing operational behaviour of the net.
2. Analysing actual weights
3. Study of network behaviour under specific conditions
Test data
Should contain training cases as well as new cases
Routine, unusual as well as boundary condition cases
should be tried ICT619 30
Implementation - Testing and
Debugging (cont’d)
Testing by weight analysis
Weights entering and exiting nodes analysed for
relatively small and large values
ICT619 32
The Maintenance Phase
ICT619 33
System evaluation
ICT619 34
ANN Maintenance
ICT619 35
ANN Maintenance (cont’d)
ICT619 36
A comparison of ANN and ES
ICT619 37
A comparison of ANN and ES
(cont’d)
Differences between ANN and ES
Differ in aspects of design, operation and use
ICT619 40
A comparison of ANN and ES
(cont’d)
ICT619 41
Hybrid systems
Neuro-symbolic computing utilises the complementary
nature of computing in neural networks (numerical) and
expert systems (symbolic).
Neuro-fuzzy systems combine neural networks with
fuzzy logic
ANNs can also be combined with genetic algorithm
methodology
ICT619 44
Hybrid ES-ANN systems (cont’d)
ICT619 47
Case Study
ICT619 50
REFERENCES (cont’d)
Bailey, D., & Thompson, D., How to Develop Neural Network
Applications, AI Expert, June 1990, pp. 38-47.
Caudill & Butler, Naturally Intelligent Systems, MIT
Press,1989, pp 227-240.
Caudill, M., “Expert networks”, BYTE pp.109-116, October
1991.
Dhar, V., & Stein, R., Seven Methods for Transforming
Corporate Data into Business Intelligence., Prentice Hall
1997.
Gallant, S., Neural Network Learning and Expert Systems,
MIT Press 1993.
Medsker,L., Hybrid Intelligent Systems, Kluwer Academic
Press, Boston 1995
Zahedi, F., Intelligent Systems for Business, Wadsworth
Publishing, , Belmont, California, 1993.
ICT619 51