Neural networks and applications tutorial.
Physics Reports , 207(3-5):215--259.
The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear.
The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks.
Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, deconvolution, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks.
The tutorial is divided into six lectures, to be presented at the Third Graduate Summer Course on Computational Physics (Sept 3-7 1990) on Par allel Architectures and Applications, organized by the European Physical Society:
Introduction: machine learning and biological computation.
Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations.
Neural network systems: architectures, learning algorithms.
Applications: pattern recognition, signal processing, etc.
Elements of learning theory: how to build networks which generalize.
A case study: a neural network for on-line recognition of hand-printed alphanumeric characters.
[ next paper ]