Extraction of Feature Attentive Regions in a Learnt Neural Network
Summary :
This paper proposes a new method of extracting feature attentive regions in a learnt multi-layer neural network. We difine a function which calculates the degree of dependence of an output unit on an inpur unit. The value of this function can be used to investigate whether a learnt network detects the feature regions in the training patterns. Three computer simulations are presented: (1) investigation of the basic characteristic of this function; (2) application of our method to a simpie pattern classification task; (3) application of our method to a large scale pattern classfication task.
- Publication
- IEICE TRANSACTIONS on Information Vol.E77-D No.4 pp.482-489
- Publication Date
- 1994/04/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Issue on Neurocomputing)
- Category
- Image Processing
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
Hideki SANO, Atsuhiro NADA, Yuji IWAHORI, Naohiro ISHII, "Extraction of Feature Attentive Regions in a Learnt Neural Network" in IEICE TRANSACTIONS on Information,
vol. E77-D, no. 4, pp. 482-489, April 1994, doi: .
Abstract: This paper proposes a new method of extracting feature attentive regions in a learnt multi-layer neural network. We difine a function which calculates the degree of dependence of an output unit on an inpur unit. The value of this function can be used to investigate whether a learnt network detects the feature regions in the training patterns. Three computer simulations are presented: (1) investigation of the basic characteristic of this function; (2) application of our method to a simpie pattern classification task; (3) application of our method to a large scale pattern classfication task.
URL: https://global.ieice.org/en_transactions/information/10.1587/e77-d_4_482/_p
Copy
@ARTICLE{e77-d_4_482,
author={Hideki SANO, Atsuhiro NADA, Yuji IWAHORI, Naohiro ISHII, },
journal={IEICE TRANSACTIONS on Information},
title={Extraction of Feature Attentive Regions in a Learnt Neural Network},
year={1994},
volume={E77-D},
number={4},
pages={482-489},
abstract={This paper proposes a new method of extracting feature attentive regions in a learnt multi-layer neural network. We difine a function which calculates the degree of dependence of an output unit on an inpur unit. The value of this function can be used to investigate whether a learnt network detects the feature regions in the training patterns. Three computer simulations are presented: (1) investigation of the basic characteristic of this function; (2) application of our method to a simpie pattern classification task; (3) application of our method to a large scale pattern classfication task.},
keywords={},
doi={},
ISSN={},
month={April},}
Copy
TY - JOUR
TI - Extraction of Feature Attentive Regions in a Learnt Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 482
EP - 489
AU - Hideki SANO
AU - Atsuhiro NADA
AU - Yuji IWAHORI
AU - Naohiro ISHII
PY - 1994
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E77-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 1994
AB - This paper proposes a new method of extracting feature attentive regions in a learnt multi-layer neural network. We difine a function which calculates the degree of dependence of an output unit on an inpur unit. The value of this function can be used to investigate whether a learnt network detects the feature regions in the training patterns. Three computer simulations are presented: (1) investigation of the basic characteristic of this function; (2) application of our method to a simpie pattern classification task; (3) application of our method to a large scale pattern classfication task.
ER -
English
