JOURNAL ARTICLE

A new current mode programmable cellular neural network

Abstract

We report on the design of a full-analog current-mode CNN in a 1.2 /spl mu/m CMOS technology, whose cell core is characterized by an intrinsic capability of weights control, low power consumption and small area occupation. Circuit simulations allowed the design approach to be validated and the electrical performance of the CNN to be predicted; moreover, it is shown that the proposed CNN can be successfully adopted for several applications in image processing. A preliminary CNN test-chip consisting of a 8/spl times/1 array for connected component detection and shadow detection, is currently being fabricated at IRST (Trento Italy) in a 2.5 /spl mu/m CMOS technology.

Keywords:
CMOS Cellular neural network Computer science Chip Electronic engineering Power consumption Mode (computer interface) Power (physics) Integrated circuit design Shadow (psychology) Artificial neural network Electrical engineering Computer hardware Embedded system Engineering Artificial intelligence Telecommunications Physics

Metrics

4
Cited By
0.47
FWCI (Field Weighted Citation Impact)
10
Refs
0.65
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Topics

Neural Networks Stability and Synchronization
Physical Sciences →  Computer Science →  Computer Networks and Communications
Advanced Memory and Neural Computing
Physical Sciences →  Engineering →  Electrical and Electronic Engineering
Neural Networks and Applications
Physical Sciences →  Computer Science →  Artificial Intelligence
© 2026 ScienceGate Book Chapters — All rights reserved.