Natural gradient learning for second-order nonstationary source separation

Seungjin Choi; Andrzej Cichocki; Shunichi Amari

Natural gradient learning for second-order nonstationary source separation

Seungjin Choi
, Andrzej Cichocki
, Shunichi Amari

Pohang University of Science and Technology

研究成果: 会議への寄与 › 論文 › 査読

3 被引用数 (Scopus)

抄録

In this paper we consider a problem of source separation when sources are second-order non-stationary stochastic processes. We employ the natural gradient method and develop learning algorithms for both linear feedback and feedforward neural networks. Thus our algorithms possess equivariant property. Local stability analysis shows that separating solutions are always locally stable stationary points of the proposed algorithms, regardless of probability distributions of sources.

本文言語	英語
ページ	654-658
ページ数	5
出版ステータス	出版済み - 2002
外部発表	はい
イベント	2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, 米国継続期間: 12 5月 2002 → 17 5月 2002

会議

会議	2002 International Joint Conference on Neural Networks (IJCNN '02)
国/地域	米国
City	Honolulu, HI
Period	12/05/02 → 17/05/02

他のファイルとリンク

Scopusの出版物のリンク

引用スタイル

@conference{1a2e71cff8ab4050900a3ed540e3c0b7,

title = "Natural gradient learning for second-order nonstationary source separation",

abstract = "In this paper we consider a problem of source separation when sources are second-order non-stationary stochastic processes. We employ the natural gradient method and develop learning algorithms for both linear feedback and feedforward neural networks. Thus our algorithms possess equivariant property. Local stability analysis shows that separating solutions are always locally stable stationary points of the proposed algorithms, regardless of probability distributions of sources.",

author = "Seungjin Choi and Andrzej Cichocki and Shunichi Amari",

year = "2002",

language = "英語",

pages = "654--658",

note = "2002 International Joint Conference on Neural Networks (IJCNN '02) ; Conference date: 12-05-2002 Through 17-05-2002",

}

TY - CONF

T1 - Natural gradient learning for second-order nonstationary source separation

AU - Choi, Seungjin

AU - Cichocki, Andrzej

AU - Amari, Shunichi

PY - 2002

Y1 - 2002

N2 - In this paper we consider a problem of source separation when sources are second-order non-stationary stochastic processes. We employ the natural gradient method and develop learning algorithms for both linear feedback and feedforward neural networks. Thus our algorithms possess equivariant property. Local stability analysis shows that separating solutions are always locally stable stationary points of the proposed algorithms, regardless of probability distributions of sources.

AB - In this paper we consider a problem of source separation when sources are second-order non-stationary stochastic processes. We employ the natural gradient method and develop learning algorithms for both linear feedback and feedforward neural networks. Thus our algorithms possess equivariant property. Local stability analysis shows that separating solutions are always locally stable stationary points of the proposed algorithms, regardless of probability distributions of sources.

UR - https://www.scopus.com/pages/publications/0036073304

M3 - 論文

AN - SCOPUS:0036073304

SP - 654

EP - 658

T2 - 2002 International Joint Conference on Neural Networks (IJCNN '02)

Y2 - 12 May 2002 through 17 May 2002

ER -

Natural gradient learning for second-order nonstationary source separation

抄録

会議

他のファイルとリンク

フィンガープリント

引用スタイル