PNNL

Abstract

This tutorial text introduces the reader to the fascinating world of artificial neural networks. It is a journey that we are here to help you with. After all the many neural network books that have been written, why write this one? We have written it for the reader who wants to understand artificial neural networks without being bogged down in the mathematics behind it all. For those who desire the math, we have included sufficient detail in the appendices for most of the common neural network algorithms. The concept of data driven computing is the overriding principal upon which neural networks have been built. We see many problems in the world where there is lots of data but no underlying knowledge of the process that converts the measured inputs into the observed outputs. Artificial neural networks are well suited to this class of problem because they are excellent data mappers in that they map inputs to outputs. This text illustrates how this is done with examples and relevant snippets of theory. We have enjoyed writing the text and welcome all who read this preface to dig further and learn how artificial neural networks are changing the world around us.