Injection of external information to feature maps of multiply descent cost competitive learning

Yasuo Matsuyama, Yasushi Kurosawa

研究成果: Conference contribution

抄録

Multiple descent cost competitive learning simultaneously generates two types of feature maps by self-organization. One is a grouped pattern of atomic data elements; the other is a geometric structure on the set of neural weight vectors. In the case of images, the grouped pattern is a set of nonoverlapping quadrilaterals. Each quadrilateral is associated with a neural weight vector, i.e., an image patch. Then, control of the grouped pattern based on external intelligence creates new images. By this method, generation of new emotional features on facial images is attempted. Thus, the feature map of the multiple descent cost competitive learning is not used for recognition but is utilized for creation of new patterns by incorporating additional information.

元の言語English
ホスト出版物のタイトル91 IEEE Int Jt Conf Neural Networks IJCNN 91
出版場所Piscataway, NJ, United States
出版者Publ by IEEE
ページ994-1000
ページ数7
ISBN(印刷物)0780302273
出版物ステータスPublished - 1991
外部発表Yes
イベント1991 IEEE International Joint Conference on Neural Networks - IJCNN '91 - Singapore, Singapore
継続期間: 1991 11 181991 11 21

Other

Other1991 IEEE International Joint Conference on Neural Networks - IJCNN '91
Singapore, Singapore
期間91/11/1891/11/21

Fingerprint

Costs

ASJC Scopus subject areas

  • Engineering(all)

これを引用

Matsuyama, Y., & Kurosawa, Y. (1991). Injection of external information to feature maps of multiply descent cost competitive learning. : 91 IEEE Int Jt Conf Neural Networks IJCNN 91 (pp. 994-1000). Piscataway, NJ, United States: Publ by IEEE.

Injection of external information to feature maps of multiply descent cost competitive learning. / Matsuyama, Yasuo; Kurosawa, Yasushi.

91 IEEE Int Jt Conf Neural Networks IJCNN 91. Piscataway, NJ, United States : Publ by IEEE, 1991. p. 994-1000.

研究成果: Conference contribution

Matsuyama, Y & Kurosawa, Y 1991, Injection of external information to feature maps of multiply descent cost competitive learning. : 91 IEEE Int Jt Conf Neural Networks IJCNN 91. Publ by IEEE, Piscataway, NJ, United States, pp. 994-1000, 1991 IEEE International Joint Conference on Neural Networks - IJCNN '91, Singapore, Singapore, 91/11/18.
Matsuyama Y, Kurosawa Y. Injection of external information to feature maps of multiply descent cost competitive learning. : 91 IEEE Int Jt Conf Neural Networks IJCNN 91. Piscataway, NJ, United States: Publ by IEEE. 1991. p. 994-1000
Matsuyama, Yasuo ; Kurosawa, Yasushi. / Injection of external information to feature maps of multiply descent cost competitive learning. 91 IEEE Int Jt Conf Neural Networks IJCNN 91. Piscataway, NJ, United States : Publ by IEEE, 1991. pp. 994-1000
@inproceedings{6d7dc04b2f814c038a268c399ac43a44,
title = "Injection of external information to feature maps of multiply descent cost competitive learning",
abstract = "Multiple descent cost competitive learning simultaneously generates two types of feature maps by self-organization. One is a grouped pattern of atomic data elements; the other is a geometric structure on the set of neural weight vectors. In the case of images, the grouped pattern is a set of nonoverlapping quadrilaterals. Each quadrilateral is associated with a neural weight vector, i.e., an image patch. Then, control of the grouped pattern based on external intelligence creates new images. By this method, generation of new emotional features on facial images is attempted. Thus, the feature map of the multiple descent cost competitive learning is not used for recognition but is utilized for creation of new patterns by incorporating additional information.",
author = "Yasuo Matsuyama and Yasushi Kurosawa",
year = "1991",
language = "English",
isbn = "0780302273",
pages = "994--1000",
booktitle = "91 IEEE Int Jt Conf Neural Networks IJCNN 91",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Injection of external information to feature maps of multiply descent cost competitive learning

AU - Matsuyama, Yasuo

AU - Kurosawa, Yasushi

PY - 1991

Y1 - 1991

N2 - Multiple descent cost competitive learning simultaneously generates two types of feature maps by self-organization. One is a grouped pattern of atomic data elements; the other is a geometric structure on the set of neural weight vectors. In the case of images, the grouped pattern is a set of nonoverlapping quadrilaterals. Each quadrilateral is associated with a neural weight vector, i.e., an image patch. Then, control of the grouped pattern based on external intelligence creates new images. By this method, generation of new emotional features on facial images is attempted. Thus, the feature map of the multiple descent cost competitive learning is not used for recognition but is utilized for creation of new patterns by incorporating additional information.

AB - Multiple descent cost competitive learning simultaneously generates two types of feature maps by self-organization. One is a grouped pattern of atomic data elements; the other is a geometric structure on the set of neural weight vectors. In the case of images, the grouped pattern is a set of nonoverlapping quadrilaterals. Each quadrilateral is associated with a neural weight vector, i.e., an image patch. Then, control of the grouped pattern based on external intelligence creates new images. By this method, generation of new emotional features on facial images is attempted. Thus, the feature map of the multiple descent cost competitive learning is not used for recognition but is utilized for creation of new patterns by incorporating additional information.

UR - http://www.scopus.com/inward/record.url?scp=0026287764&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026287764&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026287764

SN - 0780302273

SP - 994

EP - 1000

BT - 91 IEEE Int Jt Conf Neural Networks IJCNN 91

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -