Name
Abstract | ||
|---|---|---|
In this paper we propose and develop a fully programmable CNN circuit. The CNN coefficients are digitally programmable using a Digital to Analog Converter (DAC), resulting in added flexibility.CNNs with 4x4 and 16x16 cells are designed and tested, exhibiting good accuracy when compared with Matlab and Java applications for computing CNNs.All circuits are designed and implemented with a 0.35um CMOS technology. The layout of a full 4x4 CNN was designed using Cadence Design Framework II. The circuits are simulated with Pspice/Spectre. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1145/1016568.1016620 | SBCCI |
Keywords | Field | DocType |
analog converter,added flexibility,java application,cnn coefficient,cadence design framework ii,programmable cnn circuit,programmable cellular neural network,cmos technology,good accuracy,integrated circuit layout,microelectronics,neural network,vlsi,cellular neural network,cellular neural networks | Integrated circuit layout,MATLAB,Spice,Computer science,Electronic engineering,CMOS,Digital-to-analog converter,Electronic circuit,Very-large-scale integration,Cellular neural network | Conference |
ISBN | Citations | PageRank |
1-58113-947-0 | 2 | 1.08 |
References | Authors | |
3 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Michel Leong | 1 | 2 | 1.08 |
| Pedro Vasconcelos | 2 | 27 | 2.76 |
| Jorge R. Fernandes | 3 | 154 | 34.16 |
| Leonel Sousa | 4 | 1210 | 145.50 |