Design of Fully Analogue Artificial Neural Network with Learning Based on Backpropagation
Loading...
Date
2021-06
Authors
ORCID
Advisor
Referee
Mark
Journal Title
Journal ISSN
Volume Title
Publisher
Společnost pro radioelektronické inženýrství
Altmetrics
Abstract
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.
Description
Citation
Radioengineering. 2021 vol. 30, č. 2, s. 357-363. ISSN 1210-2512
https://www.radioeng.cz/fulltexts/2021/21_02_0357_0363.pdf
https://www.radioeng.cz/fulltexts/2021/21_02_0357_0363.pdf
Document type
Peer-reviewed
Document version
Published version
Date of access to the full text
Language of document
en