Tóm tắt:

This paper presents the algorithms for training an artificial neural network (ANN) for regression analysis; the algorithm is based on the generalized delta rule. The training method of a simple neuron model and an ANN model are presented and generalized. The models are then programed in Visual C# .NET and applied to predict the compressive strength of concrete mixes. Three datasets, collected from the literature, are used to demonstrate the applications of the models.