The original CNN paradigm was first proposed by Chua and Yang in 1988. The two most fundamental ingredients of the CNN paradigm are:

Architecture of Cellular Neural Networks

The basic circuit unit of a CNN is called a cell. It contains linear
and nonlinear circuit elements, which typically are linear capacitors,
linear resistors, linear and nonlinear controlled sources, and independent
sources.

Global behavior of Cellular Neural Networks

Assuming that the interconnections of a single cell do not depend on
its position, the global behavior of a CNN is described by its Template
set containing the A-Template, the B-Template, the Bias I,
and the initial state.

Application Potential

A CNN is very well suited for high speed parallel signal processing.
Its local interconnection feature makes it tailor-made for VLSI implementation.

Potential applications for Cellular Neural Networks are signal processing,
pattern recognition and image processing.

back to head page . . .