Design of Fully Analogue Artificial Neural Network with Learning Based on Backpropagation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00350555" target="_blank" >RIV/68407700:21230/21:00350555 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.13164/re.2021.0357" target="_blank" >https://doi.org/10.13164/re.2021.0357</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.13164/re.2021.0357" target="_blank" >10.13164/re.2021.0357</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Design of Fully Analogue Artificial Neural Network with Learning Based on Backpropagation

Popis výsledku v původním jazyce

A fully analogue implementation of training algorithms would speed up the training of artificial neural networks. A common choice for training the feedforward networks is the backpropagation with stochastic gradient descent. However, the circuit design that would enable its analogue implementation is still an open problem. This paper proposes a fully analogue training circuit block concept based on the backpropagation for neural networks without clock control. Capacitors are used as memory elements for the presented example. The XOR problem is used as an example for concept-level system validation.

Název v anglickém jazyce

Design of Fully Analogue Artificial Neural Network with Learning Based on Backpropagation

Popis výsledku anglicky

A fully analogue implementation of training algorithms would speed up the training of artificial neural networks. A common choice for training the feedforward networks is the backpropagation with stochastic gradient descent. However, the circuit design that would enable its analogue implementation is still an open problem. This paper proposes a fully analogue training circuit block concept based on the backpropagation for neural networks without clock control. Capacitors are used as memory elements for the presented example. The XOR problem is used as an example for concept-level system validation.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Radioengineering

ISSN

1210-2512

e-ISSN

1805-9600

Svazek periodika

2021

Číslo periodika v rámci svazku

30

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

7

Strana od-do

357-363

Kód UT WoS článku

000719147800012

EID výsledku v databázi Scopus

2-s2.0-85108525300