ABSTRACT
For many decades it has been a goal of science and engineering to develop intelligent machines with a large number of simple elements. References to this subject can be found even in the scientific literature of the nineteenth century. During the 1940s, researchers desiring to duplicate the function of the human brain developed simple hardware (and later software) models of biological neurons and their interconnection system. McCulloch and Pitts (1943) published the first systematic study of the artificial neural network (NN). Four years latter McCulloch and Pitts (1947) explored network paradigms for pattern recognition using a single layer perceptron. However, from I960 to 1980, due to severe restrictions on what a perceptron can represent, neural network research went into near eclipse. The recent discovery of training methods for multilayer methods has, more than any other factor, been responsible for the recent resurgence of interest in the neural network.
