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

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

3 Scopus citations

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.

Original language	English
Pages	654-658
Number of pages	5
State	Published - 2002
Externally published	Yes
Event	2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States Duration: 12 May 2002 → 17 May 2002

Conference

Conference	2002 International Joint Conference on Neural Networks (IJCNN '02)
Country/Territory	United States
City	Honolulu, HI
Period	12/05/02 → 17/05/02

Cite this

@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

Abstract

Conference

Other files and links

Fingerprint

Cite this