Artificial neural networks are mathematical inventions inspired by observations made in the study of biological systems, though loosely based on the actual biology. An artificial neural network can be described as mapping an input space to an output space. This concept is analogous to that of a mathematical function. The purpose of a neural network is to map an input into a desired output. While patterned after the interconnections between neurons found in biological systems, artificial neural networks are no more related to real neurons than feathers are related to modern airplanes. Both biological systems, neurons and feathers, serve a useful purpose, but the implementation of the principles involved has resulted in man-made inventions that bear little resemblance to the biological systems that spawned the creative process.
This text starts with the aim of introducing the reader to many of the most popular artificial neural networks while keeping the mathematical gymnastics to a minimum. Many excellent texts, which have detailed mathematical descriptions for many of the artificial neural networks presented in this book, are cited in the bibliography. Additional mathematical background for the neural-network algorithms is provided in the appendixes as well. Artificial neural networks are modeled after early observations in biological systems: myriads of neurons, all connected in a manner that somehow distributes the necessary signals to various parts of the body to allow the biological system to function and survive. No one knows exactly how the brain works or what is happening in the nervous system all of the time, but scientists and medical doctors have been able to uncover the inner workings of the mind and the nervous system to a degree that allows them to completely describe the operation of the basic computational building block of the nervous system and brain: the neuron.
Online access to SPIE eBooks is limited to subscribing institutions.