Design of Fully Analogue Artificial Neural Network with Learning Based on Backpropagation
The result's identifiers
Result code in 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>
Result on the web
<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>
Alternative languages
Result language
angličtina
Original language name
Design of Fully Analogue Artificial Neural Network with Learning Based on Backpropagation
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
20201 - Electrical and electronic engineering
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Radioengineering
ISSN
1210-2512
e-ISSN
1805-9600
Volume of the periodical
2021
Issue of the periodical within the volume
30
Country of publishing house
CZ - CZECH REPUBLIC
Number of pages
7
Pages from-to
357-363
UT code for WoS article
000719147800012
EID of the result in the Scopus database
2-s2.0-85108525300