Neural network model of the binocular fusion in the human vision

Jinglong Wu, Yoshikazu Nishikawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a model of the binocular fusion based on the psychological experimental results and the physiological knowledge. Considering the psychological results and the physiological structure, we assume that the binocular information are processed by several binocular channel having different spatial characteristics from low spatial frequency to high spatial frequency. In order to examine the mechanism of the binocular fusion, we construct a five layer neural network model, and train it by the back-propagation learning algorithm with use of psychological experimental data. After completion of learning, the generalization capability of the network are examined. Further, the response functions of the hidden units have been examined, which suggested that the hidden units have spatial selective characteristic. In other words, the binocular information is considered to be pressed of parallel channels with different spatial characteristics.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages4169-4174
Number of pages6
Volume6
Publication statusPublished - 1994
Externally publishedYes
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: Jun 27 1994Jun 29 1994

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period6/27/946/29/94

Fingerprint

Binoculars
Fusion reactions
Neural networks
Backpropagation
Learning algorithms

ASJC Scopus subject areas

  • Software

Cite this

Wu, J., & Nishikawa, Y. (1994). Neural network model of the binocular fusion in the human vision. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 6, pp. 4169-4174). IEEE.

Neural network model of the binocular fusion in the human vision. / Wu, Jinglong; Nishikawa, Yoshikazu.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 6 IEEE, 1994. p. 4169-4174.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wu, J & Nishikawa, Y 1994, Neural network model of the binocular fusion in the human vision. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 6, IEEE, pp. 4169-4174, Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, 6/27/94.
Wu J, Nishikawa Y. Neural network model of the binocular fusion in the human vision. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 6. IEEE. 1994. p. 4169-4174
Wu, Jinglong ; Nishikawa, Yoshikazu. / Neural network model of the binocular fusion in the human vision. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 6 IEEE, 1994. pp. 4169-4174
@inproceedings{49fba3516f3046c6a853f8b2b51b0593,
title = "Neural network model of the binocular fusion in the human vision",
abstract = "This paper proposes a model of the binocular fusion based on the psychological experimental results and the physiological knowledge. Considering the psychological results and the physiological structure, we assume that the binocular information are processed by several binocular channel having different spatial characteristics from low spatial frequency to high spatial frequency. In order to examine the mechanism of the binocular fusion, we construct a five layer neural network model, and train it by the back-propagation learning algorithm with use of psychological experimental data. After completion of learning, the generalization capability of the network are examined. Further, the response functions of the hidden units have been examined, which suggested that the hidden units have spatial selective characteristic. In other words, the binocular information is considered to be pressed of parallel channels with different spatial characteristics.",
author = "Jinglong Wu and Yoshikazu Nishikawa",
year = "1994",
language = "English",
volume = "6",
pages = "4169--4174",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Neural network model of the binocular fusion in the human vision

AU - Wu, Jinglong

AU - Nishikawa, Yoshikazu

PY - 1994

Y1 - 1994

N2 - This paper proposes a model of the binocular fusion based on the psychological experimental results and the physiological knowledge. Considering the psychological results and the physiological structure, we assume that the binocular information are processed by several binocular channel having different spatial characteristics from low spatial frequency to high spatial frequency. In order to examine the mechanism of the binocular fusion, we construct a five layer neural network model, and train it by the back-propagation learning algorithm with use of psychological experimental data. After completion of learning, the generalization capability of the network are examined. Further, the response functions of the hidden units have been examined, which suggested that the hidden units have spatial selective characteristic. In other words, the binocular information is considered to be pressed of parallel channels with different spatial characteristics.

AB - This paper proposes a model of the binocular fusion based on the psychological experimental results and the physiological knowledge. Considering the psychological results and the physiological structure, we assume that the binocular information are processed by several binocular channel having different spatial characteristics from low spatial frequency to high spatial frequency. In order to examine the mechanism of the binocular fusion, we construct a five layer neural network model, and train it by the back-propagation learning algorithm with use of psychological experimental data. After completion of learning, the generalization capability of the network are examined. Further, the response functions of the hidden units have been examined, which suggested that the hidden units have spatial selective characteristic. In other words, the binocular information is considered to be pressed of parallel channels with different spatial characteristics.

UR - http://www.scopus.com/inward/record.url?scp=0028706640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028706640&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0028706640

VL - 6

SP - 4169

EP - 4174

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -