On-line adaptive algorithms in non-stationary environments using a modified conjugate gradient approach

Andrzej Cichocki; Bruno Orsier; Andrew Back; Shun ichi Amari

On-line adaptive algorithms in non-stationary environments using a modified conjugate gradient approach

Andrzej Cichocki, Bruno Orsier, Andrew Back, Shun ichi Amari

RIKEN

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

14 Scopus citations

Abstract

In this paper we propose novel computationally efficient schemas for a large class of on-line adaptive algorithms with variable self-adaptive learning rates. The learning rate is adjusted automatically providing relatively fast convergence at early stages of adaptation while ensuring small final misadjustment for cases of stationary environments. For non-stationary environments, the algorithms proposed have good tracking ability and quick adaptation to new conditions. Their validity and efficiency are illustrated for a non-stationary blind separation problem.

Original language	English
Pages	316-325
Number of pages	10
State	Published - 1997
Externally published	Yes
Event	Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97 - Amelia Island, FL, USA Duration: 24 Sep 1997 → 26 Sep 1997

Conference

Conference	Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97
City	Amelia Island, FL, USA
Period	24/09/97 → 26/09/97

Cite this

@conference{ae6bc8891a8d4b4da2b1b88f99e956df,

title = "On-line adaptive algorithms in non-stationary environments using a modified conjugate gradient approach",

abstract = "In this paper we propose novel computationally efficient schemas for a large class of on-line adaptive algorithms with variable self-adaptive learning rates. The learning rate is adjusted automatically providing relatively fast convergence at early stages of adaptation while ensuring small final misadjustment for cases of stationary environments. For non-stationary environments, the algorithms proposed have good tracking ability and quick adaptation to new conditions. Their validity and efficiency are illustrated for a non-stationary blind separation problem.",

author = "Andrzej Cichocki and Bruno Orsier and Andrew Back and Amari, \{Shun ichi\}",

year = "1997",

language = "英語",

pages = "316--325",

note = "Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97 ; Conference date: 24-09-1997 Through 26-09-1997",

}

On-line adaptive algorithms in non-stationary environments using a modified conjugate gradient approach. / Cichocki, Andrzej; Orsier, Bruno; Back, Andrew et al.
1997. 316-325 Paper presented at Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97, Amelia Island, FL, USA.

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

TY - CONF

T1 - On-line adaptive algorithms in non-stationary environments using a modified conjugate gradient approach

AU - Cichocki, Andrzej

AU - Orsier, Bruno

AU - Back, Andrew

AU - Amari, Shun ichi

PY - 1997

Y1 - 1997

N2 - In this paper we propose novel computationally efficient schemas for a large class of on-line adaptive algorithms with variable self-adaptive learning rates. The learning rate is adjusted automatically providing relatively fast convergence at early stages of adaptation while ensuring small final misadjustment for cases of stationary environments. For non-stationary environments, the algorithms proposed have good tracking ability and quick adaptation to new conditions. Their validity and efficiency are illustrated for a non-stationary blind separation problem.

AB - In this paper we propose novel computationally efficient schemas for a large class of on-line adaptive algorithms with variable self-adaptive learning rates. The learning rate is adjusted automatically providing relatively fast convergence at early stages of adaptation while ensuring small final misadjustment for cases of stationary environments. For non-stationary environments, the algorithms proposed have good tracking ability and quick adaptation to new conditions. Their validity and efficiency are illustrated for a non-stationary blind separation problem.

UR - https://www.scopus.com/pages/publications/0031334055

M3 - 論文

AN - SCOPUS:0031334055

SP - 316

EP - 325

T2 - Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97

Y2 - 24 September 1997 through 26 September 1997

ER -

On-line adaptive algorithms in non-stationary environments using a modified conjugate gradient approach

Abstract

Conference

Other files and links

Fingerprint

Cite this