A LOW-POWER CMOS IMPLEMENTATION OF PROGRAMMABLE CNNS WITH EMBEDDED PHOTOSENSORS

In this brief, an analog CMOS implementation of a Cellular Neural Netw ork (CNN) is presented, which is based on a combination of MOS transis tors operating in different modes: weak and strong-inversion and MOS t ransistors operated in the lateral bipolar mode. This combination has enabled a VLSI implementation of a simplified version of the original CNN model with the main characteristics of low-power consumption, prog rammability, and embedded photosensors to process images directly proj ected on the chip. An 8 x 8-cell CNN chip prototype is reported with e xperimental results for different image processing tasks, A density of 10.7 cells/mm(2) in a 1.2-mu m CMOS technology and a power consumptio n of tens of microwatts per cell are obtained.