Ahmad, M. A. and Saleh, J Mohamad (2004) Software Toolkit For Designing An Artificial Neural Network. In: 1st National Postgraduate Colloquium, 2004, School of Chemical Engineering, USM .
Basically, there are two kinds of artificial neural network (ANN), which can be classified into supervised and unsupervised. Commonly, supervised neural networks are trained or weights adjusted, so that a particular input leads to a specific target output. Generally, the supervised training methods are commonly used in solving most problems. An ANN can be designed, trained, validated and tested by means of the Neural Network Toolbox in Matlab.
Actions (login required)