High-Accuracy Gaussian Function Generator for Neural Networks
A new improved accuracy CMOS Gaussian function generator will be presented. The original sixth-order approximation function that represents the basis for designing the proposed Gaussian circuit allows a large increase in the circuit accuracy and also of the input variable maximal range. The original...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/1/24 |
_version_ | 1797626048997752832 |
---|---|
author | Cosmin Radu Popa |
author_facet | Cosmin Radu Popa |
author_sort | Cosmin Radu Popa |
collection | DOAJ |
description | A new improved accuracy CMOS Gaussian function generator will be presented. The original sixth-order approximation function that represents the basis for designing the proposed Gaussian circuit allows a large increase in the circuit accuracy and also of the input variable maximal range. The original proposed computational structure has a large dynamic output range of 27 dB, for a variation smaller than 1 dB as compared with the ideal Gaussian function. The circuit is simulated for 0.18 μm CMOS technology and has a low supply voltage (V<sub>DD</sub> = 0.7 V). Its power consumption is smaller than 0.22 μW, for V<sub>DD</sub> = 0.7 V, while the chip area is about 7 μm<sup>2</sup>. The new proposed architecture is re-configurable, the convenient modification of the coefficients allowing to obtain many mathematical functions using the same computational structure. |
first_indexed | 2024-03-11T10:05:06Z |
format | Article |
id | doaj.art-952ceb6ce7884731b5e9d3252e520ed1 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-11T10:05:06Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-952ceb6ce7884731b5e9d3252e520ed12023-11-16T15:10:03ZengMDPI AGElectronics2079-92922022-12-011212410.3390/electronics12010024High-Accuracy Gaussian Function Generator for Neural NetworksCosmin Radu Popa0Faculty of Electronics, Telecommunications and Information Technology, Politehnica University of Bucharest, 061071 Bucharest, RomaniaA new improved accuracy CMOS Gaussian function generator will be presented. The original sixth-order approximation function that represents the basis for designing the proposed Gaussian circuit allows a large increase in the circuit accuracy and also of the input variable maximal range. The original proposed computational structure has a large dynamic output range of 27 dB, for a variation smaller than 1 dB as compared with the ideal Gaussian function. The circuit is simulated for 0.18 μm CMOS technology and has a low supply voltage (V<sub>DD</sub> = 0.7 V). Its power consumption is smaller than 0.22 μW, for V<sub>DD</sub> = 0.7 V, while the chip area is about 7 μm<sup>2</sup>. The new proposed architecture is re-configurable, the convenient modification of the coefficients allowing to obtain many mathematical functions using the same computational structure.https://www.mdpi.com/2079-9292/12/1/24Gaussian functionVLSI neural networksanalog signal processingapproximation functioncurrent-mode operation |
spellingShingle | Cosmin Radu Popa High-Accuracy Gaussian Function Generator for Neural Networks Electronics Gaussian function VLSI neural networks analog signal processing approximation function current-mode operation |
title | High-Accuracy Gaussian Function Generator for Neural Networks |
title_full | High-Accuracy Gaussian Function Generator for Neural Networks |
title_fullStr | High-Accuracy Gaussian Function Generator for Neural Networks |
title_full_unstemmed | High-Accuracy Gaussian Function Generator for Neural Networks |
title_short | High-Accuracy Gaussian Function Generator for Neural Networks |
title_sort | high accuracy gaussian function generator for neural networks |
topic | Gaussian function VLSI neural networks analog signal processing approximation function current-mode operation |
url | https://www.mdpi.com/2079-9292/12/1/24 |
work_keys_str_mv | AT cosminradupopa highaccuracygaussianfunctiongeneratorforneuralnetworks |