2.Regression. A neural network can be trained to predict an output variable whose values are of numeric (,e., real or integer numbers) type.
If a network fits well in modeling a known sequence of values, it can be used to predict future results.
An obvious example of the regression task is stock market index predictions.
Type of ANN obvious for this task include feedforward network (such as MLP with backpropagation leaning)and radial basis functions.