Prediction using neural networks

The advantage of the usage of neural networks for prediction is that they are able to learn from examples only and that after their learning is finished, they are able to catch hidden and strongly non-linear dependencies, even when there is a significant noise in the training set.

The disadvantage is that NNs can learn the dependency valid in a certain period only. The error of prediction cannot be generally estimated.

Previous - Types of prediction           Next - Neural network training

(c) Marek Obitko, 1999 - Terms of use