IEICE TRANSACTIONS on transactions
Switched-Capacitor Neural Networks and Their Application to Character Recognition
Summary :
Recently, the hardware realizations of the neural networks for specially-purposed-use have been in focus. In this paper, two kinds of networks, a two-layer network and the Boltzmann machine, using the switched-capacitor circuit are proposed. The variable synaptic weights of neural circuit are realized by through the programmable capacitor array (PCA) in the switched-capacitor variable-coefficients multiplier. As a result, the recognition system of the handwritten character using a two-layer neural network is constructed by the discrete electronic elements and its desirable effects are shown by the experimental results. The stochastic operation in the processing element (PE) of the Boltzmann machine is realized by using the generation of noise voltage with the random number and is also confirmed by teh experimental results using the discrete electronic elements. Furthermore, the operations of the PE have been also confirmed by using the simulation of Traveling-Salesman Problem.
- Publication
- IEICE TRANSACTIONS on transactions Vol.E73-E No.12 pp.1932-1939
- Publication Date
- 1990/12/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Issue on the 3rd Karuizawa Workshop on Circuits and Systems)
- Category
- Neural Networks
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yoichiro ANZAI, Koichi MATSUMOTO, Shojiro YONEDA, Akio OGIHARA, "Switched-Capacitor Neural Networks and Their Application to Character Recognition" in IEICE TRANSACTIONS on transactions,
vol. E73-E, no. 12, pp. 1932-1939, December 1990, doi: .
Abstract: Recently, the hardware realizations of the neural networks for specially-purposed-use have been in focus. In this paper, two kinds of networks, a two-layer network and the Boltzmann machine, using the switched-capacitor circuit are proposed. The variable synaptic weights of neural circuit are realized by through the programmable capacitor array (PCA) in the switched-capacitor variable-coefficients multiplier. As a result, the recognition system of the handwritten character using a two-layer neural network is constructed by the discrete electronic elements and its desirable effects are shown by the experimental results. The stochastic operation in the processing element (PE) of the Boltzmann machine is realized by using the generation of noise voltage with the random number and is also confirmed by teh experimental results using the discrete electronic elements. Furthermore, the operations of the PE have been also confirmed by using the simulation of Traveling-Salesman Problem.
URL: https://global.ieice.org/en_transactions/transactions/10.1587/e73-e_12_1932/_p
Copy
@ARTICLE{e73-e_12_1932,
author={Yoichiro ANZAI, Koichi MATSUMOTO, Shojiro YONEDA, Akio OGIHARA, },
journal={IEICE TRANSACTIONS on transactions},
title={Switched-Capacitor Neural Networks and Their Application to Character Recognition},
year={1990},
volume={E73-E},
number={12},
pages={1932-1939},
abstract={Recently, the hardware realizations of the neural networks for specially-purposed-use have been in focus. In this paper, two kinds of networks, a two-layer network and the Boltzmann machine, using the switched-capacitor circuit are proposed. The variable synaptic weights of neural circuit are realized by through the programmable capacitor array (PCA) in the switched-capacitor variable-coefficients multiplier. As a result, the recognition system of the handwritten character using a two-layer neural network is constructed by the discrete electronic elements and its desirable effects are shown by the experimental results. The stochastic operation in the processing element (PE) of the Boltzmann machine is realized by using the generation of noise voltage with the random number and is also confirmed by teh experimental results using the discrete electronic elements. Furthermore, the operations of the PE have been also confirmed by using the simulation of Traveling-Salesman Problem.},
keywords={},
doi={},
ISSN={},
month={December},}
Copy
TY - JOUR
TI - Switched-Capacitor Neural Networks and Their Application to Character Recognition
T2 - IEICE TRANSACTIONS on transactions
SP - 1932
EP - 1939
AU - Yoichiro ANZAI
AU - Koichi MATSUMOTO
AU - Shojiro YONEDA
AU - Akio OGIHARA
PY - 1990
DO -
JO - IEICE TRANSACTIONS on transactions
SN -
VL - E73-E
IS - 12
JA - IEICE TRANSACTIONS on transactions
Y1 - December 1990
AB - Recently, the hardware realizations of the neural networks for specially-purposed-use have been in focus. In this paper, two kinds of networks, a two-layer network and the Boltzmann machine, using the switched-capacitor circuit are proposed. The variable synaptic weights of neural circuit are realized by through the programmable capacitor array (PCA) in the switched-capacitor variable-coefficients multiplier. As a result, the recognition system of the handwritten character using a two-layer neural network is constructed by the discrete electronic elements and its desirable effects are shown by the experimental results. The stochastic operation in the processing element (PE) of the Boltzmann machine is realized by using the generation of noise voltage with the random number and is also confirmed by teh experimental results using the discrete electronic elements. Furthermore, the operations of the PE have been also confirmed by using the simulation of Traveling-Salesman Problem.
ER -
English
