IEICE TRANSACTIONS on Fundamentals
Three-Dimensional Quaternionic Hopfield Neural Networks
Summary :
Quaternionic neural networks are extensions of neural networks using quaternion algebra. 3-D and 4-D quaternionic MLPs have been studied. 3-D quaternionic neural networks are useful for handling 3-D objects, such as Euclidean transformation. As for Hopfield neural networks, only 4-D quaternionic Hopfield neural networks (QHNNs) have been studied. In this work, we propose the 3-D QHNNs. Moreover, we define the energy, and prove that it converges.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E100-A No.7 pp.1575-1577
- Publication Date
- 2017/07/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E100.A.1575
- Type of Manuscript
- LETTER
- Category
- Nonlinear Problems
Authors
Masaki KOBAYASHI
University of Yamanashi
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
Masaki KOBAYASHI, "Three-Dimensional Quaternionic Hopfield Neural Networks" in IEICE TRANSACTIONS on Fundamentals,
vol. E100-A, no. 7, pp. 1575-1577, July 2017, doi: 10.1587/transfun.E100.A.1575.
Abstract: Quaternionic neural networks are extensions of neural networks using quaternion algebra. 3-D and 4-D quaternionic MLPs have been studied. 3-D quaternionic neural networks are useful for handling 3-D objects, such as Euclidean transformation. As for Hopfield neural networks, only 4-D quaternionic Hopfield neural networks (QHNNs) have been studied. In this work, we propose the 3-D QHNNs. Moreover, we define the energy, and prove that it converges.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E100.A.1575/_p
Copy
@ARTICLE{e100-a_7_1575,
author={Masaki KOBAYASHI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Three-Dimensional Quaternionic Hopfield Neural Networks},
year={2017},
volume={E100-A},
number={7},
pages={1575-1577},
abstract={Quaternionic neural networks are extensions of neural networks using quaternion algebra. 3-D and 4-D quaternionic MLPs have been studied. 3-D quaternionic neural networks are useful for handling 3-D objects, such as Euclidean transformation. As for Hopfield neural networks, only 4-D quaternionic Hopfield neural networks (QHNNs) have been studied. In this work, we propose the 3-D QHNNs. Moreover, we define the energy, and prove that it converges.},
keywords={},
doi={10.1587/transfun.E100.A.1575},
ISSN={1745-1337},
month={July},}
Copy
TY - JOUR
TI - Three-Dimensional Quaternionic Hopfield Neural Networks
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1575
EP - 1577
AU - Masaki KOBAYASHI
PY - 2017
DO - 10.1587/transfun.E100.A.1575
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E100-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2017
AB - Quaternionic neural networks are extensions of neural networks using quaternion algebra. 3-D and 4-D quaternionic MLPs have been studied. 3-D quaternionic neural networks are useful for handling 3-D objects, such as Euclidean transformation. As for Hopfield neural networks, only 4-D quaternionic Hopfield neural networks (QHNNs) have been studied. In this work, we propose the 3-D QHNNs. Moreover, we define the energy, and prove that it converges.
ER -
English
