A parallel architecture for nonlinear adaptive filtering and pattern recognition

In the late 1950s there were two particular, closely related developments in information processing: the perceptron, based on the work of Rosenblatt (1961) and the adaptive noise canceller of Widrow and Hoff (1960). Subsequently the two ideas progressed in different ways under the patronage of different sections of the scientific community. The present paper centres on an assertion of their original common basis. In particular, the authors show how advances in the area of adaptive filters, largely driven by developments in high-speed digital hardware, can be applied to generalised perceptron-like systems. Conversely, these systems form an interesting class of nonlinear adaptive filters