A QCIF Resolution Binary I/O CNN-UM Chip

Authors:
Ari Paasio;Asko Kananen;Kari Halonen;Veikko Porra
Affiliations:
Electronic Circuit Design Laboratory, Helsinki University of Technology, P.O. Box 3000, FIN-02015 HUT, Finland;Electronic Circuit Design Laboratory, Helsinki University of Technology, P.O. Box 3000, FIN-02015 HUT, Finland;Electronic Circuit Design Laboratory, Helsinki University of Technology, P.O. Box 3000, FIN-02015 HUT, Finland;Electronic Circuit Design Laboratory, Helsinki University of Technology, P.O. Box 3000, FIN-02015 HUT, Finland
Venue:
Journal of VLSI Signal Processing Systems - Special issue on spatiotemporal signal processing with analog CNN visual microprocessors
Year:
1999

Citing 5
Cited 4

Fast and Compact 16 by 16 Cellular Neural Network Implementation

Analog Integrated Circuits and Signal Processing - Special issue: selected articles from the 1995 NORCHIP seminar
A 16 × 16 Cellular Neural Network UniversalChip: The First Complete Single-Chip Dynamic Computer Array withDistributed Memory and with Gray-Scale Input-Output

Analog Integrated Circuits and Signal Processing - Special issue: cellular neural networks and analog VLSI
A 6 × 6 Cells Interconnection-OrientedProgrammable Chip for CNN

Analog Integrated Circuits and Signal Processing - Special issue: cellular neural networks and analog VLSI
Focal-Plane and Multiple Chip VLSI Approaches to CNNs

Analog Integrated Circuits and Signal Processing - Special issue: cellular neural networks and analog VLSI
Analog VLSI Integration of Massive Parallel Processing Systems

Analog VLSI Integration of Massive Parallel Processing Systems

A massively parallel face recognition system

EURASIP Journal on Embedded Systems
CNN-type algorithms for H.264 variable block-size partitioning

Image Communication
Two Theorems on the Robust Designs for Pattern Matching CNNs

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
An expandable hardware platform for implementation of CNN-based applications

IWINAC'11 Proceedings of the 4th international conference on Interplay between natural and artificial computation: new challenges on bioinspired applications - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper isreported a Cellular Nonlinear Network Universal Machine realizationwhere there are 176 × 144 active cells. The size of thenetwork is the standardized QCIF video image format and the designis aimed to be used in segmenting video images in future video applicationsrequiring very low bit-rate for image transmission. The achieved cell densityis 3000 cells/mm^2 with a 0.25 micron standard digital CMOS process.Different building blocks inside the cell are given in detail and alsothe other implemented circuitry is thoroughly discussed.The physical realization of the design is also reported.