Cellular Neural Network

architecture (CNN) The CNN Universal Machine is a low cost,

low power, extremely high speed supercomputer on a chip. It

is at least 1000 times faster than equivalent DSP solutions

of many complex image processing tasks. It is a stored

program supercomputer where a complex sequence of image

processing algorithms is programmed and downloaded into the

chip, just like any digital computer. Because the entire

computer is integrated into a chip, no signal leaves the chip

until the image processing task is completed.

Although the CNN universal chip is based on analogue and logic

operating principles, it has an on-chip analog-to-digital

input-output interface so that at the system design and

application perspective, it can be used as a digital

component, just like a DSP. In particular, a development

system is available for rapid design and prototyping.

Moreover, a compiler, an operating system, and a

user-friendly CNN high-level language, like the C

language, have been developed which makes it easy to implement

any image processing algorithm.

[Professor Leon Chua, University of California at Berkeley].

(1995-04-27)