The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dans de nombreux problèmes d’apprentissage automatique, il est essentiel d’utiliser non seulement les données d’entraînement, mais également des connaissances a priori sur la façon dont le monde est contraint. Dans de nombreux cas, ces connaissances sont fournies sous forme de contraintes sur des données différentielles ou plus spécifiquement d'équations aux dérivées partielles (EDP). Les réseaux de neurones dotés de capacités d'apprentissage de données différentielles peuvent tirer parti de ces connaissances et intégrer facilement ces contraintes dans l'apprentissage des données de valeur d'entraînement. Dans cet article, nous rapportons une structure, un algorithme et les résultats d'expériences sur des réseaux de neurones apprenant des données différentielles.
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.
Copier
Ryusuke MASUOKA, "Neural Networks Learning Differential Data" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 6, pp. 1291-1300, June 2000, doi: .
Abstract: In many of machine learning problems, it is essential to use not only the training data, but also a priori knowledge about how the world is constrained. In many cases, such knowledge is given in the forms of constraints on differential data or more specifically partial differential equations (PDEs). Neural networks with capabilities to learn differential data can take advantage of such knowledge and easily incorporate such constraints into the learning of training value data. In this paper, we report a structure, an algorithm, and results of experiments on neural networks learing differential data.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_6_1291/_p
Copier
@ARTICLE{e83-d_6_1291,
author={Ryusuke MASUOKA, },
journal={IEICE TRANSACTIONS on Information},
title={Neural Networks Learning Differential Data},
year={2000},
volume={E83-D},
number={6},
pages={1291-1300},
abstract={In many of machine learning problems, it is essential to use not only the training data, but also a priori knowledge about how the world is constrained. In many cases, such knowledge is given in the forms of constraints on differential data or more specifically partial differential equations (PDEs). Neural networks with capabilities to learn differential data can take advantage of such knowledge and easily incorporate such constraints into the learning of training value data. In this paper, we report a structure, an algorithm, and results of experiments on neural networks learing differential data.},
keywords={},
doi={},
ISSN={},
month={June},}
Copier
TY - JOUR
TI - Neural Networks Learning Differential Data
T2 - IEICE TRANSACTIONS on Information
SP - 1291
EP - 1300
AU - Ryusuke MASUOKA
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2000
AB - In many of machine learning problems, it is essential to use not only the training data, but also a priori knowledge about how the world is constrained. In many cases, such knowledge is given in the forms of constraints on differential data or more specifically partial differential equations (PDEs). Neural networks with capabilities to learn differential data can take advantage of such knowledge and easily incorporate such constraints into the learning of training value data. In this paper, we report a structure, an algorithm, and results of experiments on neural networks learing differential data.
ER -