Recognition and geometrical on-line learning algorithm of probability distributions

Toshiaki Aida

doi:10.1109/ijcnn.2000.861300

Recognition and geometrical on-line learning algorithm of probability distributions

Research output: Contribution to conference › Paper › peer-review

Abstract

An on-line learning algorithm for probability distributions is constructed in a reparameterization invariant form. It enables us to identify the distributions which transform from one to another by reparameterization. This is an essential property not only for pattern recognition problems but also for the property of `information'. We can find the algorithm to be optimal, since conformal gauge reduces the problem to a non-covariant case.

Original language	English
Pages	175-180
Number of pages	6
DOIs	https://doi.org/10.1109/ijcnn.2000.861300
Publication status	Published - 2000
Externally published	Yes
Event	International Joint Conference on Neural Networks (IJCNN'2000) - Como, Italy Duration: Jul 24 2000 → Jul 27 2000

Other

Other	International Joint Conference on Neural Networks (IJCNN'2000)
City	Como, Italy
Period	7/24/00 → 7/27/00

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/ijcnn.2000.861300

Fingerprint Dive into the research topics of 'Recognition and geometrical on-line learning algorithm of probability distributions'. Together they form a unique fingerprint.

Cite this

@conference{8748548f01d547d3aaaa5d590f4f8374,

title = "Recognition and geometrical on-line learning algorithm of probability distributions",

abstract = "An on-line learning algorithm for probability distributions is constructed in a reparameterization invariant form. It enables us to identify the distributions which transform from one to another by reparameterization. This is an essential property not only for pattern recognition problems but also for the property of `information'. We can find the algorithm to be optimal, since conformal gauge reduces the problem to a non-covariant case.",

author = "Toshiaki Aida",

year = "2000",

doi = "10.1109/ijcnn.2000.861300",

language = "English",

pages = "175--180",

note = "International Joint Conference on Neural Networks (IJCNN'2000) ; Conference date: 24-07-2000 Through 27-07-2000",

}

TY - CONF

T1 - Recognition and geometrical on-line learning algorithm of probability distributions

AU - Aida, Toshiaki

PY - 2000

Y1 - 2000

N2 - An on-line learning algorithm for probability distributions is constructed in a reparameterization invariant form. It enables us to identify the distributions which transform from one to another by reparameterization. This is an essential property not only for pattern recognition problems but also for the property of `information'. We can find the algorithm to be optimal, since conformal gauge reduces the problem to a non-covariant case.

AB - An on-line learning algorithm for probability distributions is constructed in a reparameterization invariant form. It enables us to identify the distributions which transform from one to another by reparameterization. This is an essential property not only for pattern recognition problems but also for the property of `information'. We can find the algorithm to be optimal, since conformal gauge reduces the problem to a non-covariant case.

UR - http://www.scopus.com/inward/record.url?scp=0033699185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033699185&partnerID=8YFLogxK

U2 - 10.1109/ijcnn.2000.861300

DO - 10.1109/ijcnn.2000.861300

M3 - Paper

AN - SCOPUS:0033699185

SP - 175

EP - 180

T2 - International Joint Conference on Neural Networks (IJCNN'2000)

Y2 - 24 July 2000 through 27 July 2000

ER -

Recognition and geometrical on-line learning algorithm of probability distributions

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this