Artificial neural networks are increasingly useful computational models, consisting of highly interconnected parallel processing units. In particular, radial basis function, RBF, networks are emerging as important computational models for a broad range of applications. The Gaussian function used in RBF networks has an adjustable parameter, /spl sigma/, which specifies the diameter of the receptive field of the hidden layer neurons. The selection of /spl sigma/ is commonly carried out using heuristic techniques. The selection of /spl sigma/, as shown in this paper, plays an important role in the predictive capabilities of the RBF network. However, the use of a Gaussian function with the standard deviation of the training pattern output vector is shown to be associated with the minimum RMS error obtained using an optimum /spl sigma/ value derived using a heuristic technique. The aluminium fluoride, AlF/sub 3/, content of industrial reduction cell for aluminium production is well predicted using the RBF network with a Gaussian function /spl sigma/ value derived using the standard deviation of the training pattern output vector.
展开▼