2 Neural Network Theory - A Short Tutorial
Starting with measured data from some known or unknown source, a neural network may be trained to perform classification, estimation, simulation, and prediction of the underlying process generating the data. Hence, neural networks, or neural nets, are software tools designed to estimate relationships in data. An estimated relationship is essentially a mapping, or a function, relating raw data to its features. The Neural Networks package supports several function estimation techniques that may be described in terms of different types of neural networks and associated learning algorithms.
The general area of artificial neural networks has its roots in our understanding of the human brain. In this regard, initial concepts were based on attempts to mimic the brain's way of processing information. Efforts that followed gave rise to various models of biological neural network structures and learning algorithms. This is in contrast to the computational models found in this package, which are only concerned with artificial neural networks as a tool for solving different types of problems where unknown relationships are sought among given data. Still, much of the nomenclature in the neural network arena has its origins in biological neural networks, and thus, the original terminology will be used alongside with more traditional nomenclature from statistics and engineering.