Non-combinatorial estimation of independent autoregressive sources

Barnabás Póczos, A. Lőrincz

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Identification of mixed independent subspaces is thought to suffer from combinatorial explosion of two kinds: the minimization of mutual information between the estimated subspaces and the search for the optimal number and dimensions of the subspaces. Here we show that independent autoregressive process analysis, under certain conditions, can avoid this problem using a two-phase estimation process. We illustrate the solution by computer demonstration.

Original languageEnglish
Pages (from-to)2416-2419
Number of pages4
JournalNeurocomputing
Volume69
Issue number16-18
DOIs
Publication statusPublished - Oct 2006

Fingerprint

Explosions
Demonstrations

Keywords

  • Autoregressive process
  • Combinatorial explosion
  • Independent component analysis

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cellular and Molecular Neuroscience

Cite this

Non-combinatorial estimation of independent autoregressive sources. / Póczos, Barnabás; Lőrincz, A.

In: Neurocomputing, Vol. 69, No. 16-18, 10.2006, p. 2416-2419.

Research output: Contribution to journalArticle

Póczos, Barnabás ; Lőrincz, A. / Non-combinatorial estimation of independent autoregressive sources. In: Neurocomputing. 2006 ; Vol. 69, No. 16-18. pp. 2416-2419.
@article{71a6bee76d564362bd89782460c282da,
title = "Non-combinatorial estimation of independent autoregressive sources",
abstract = "Identification of mixed independent subspaces is thought to suffer from combinatorial explosion of two kinds: the minimization of mutual information between the estimated subspaces and the search for the optimal number and dimensions of the subspaces. Here we show that independent autoregressive process analysis, under certain conditions, can avoid this problem using a two-phase estimation process. We illustrate the solution by computer demonstration.",
keywords = "Autoregressive process, Combinatorial explosion, Independent component analysis",
author = "Barnab{\'a}s P{\'o}czos and A. Lőrincz",
year = "2006",
month = "10",
doi = "10.1016/j.neucom.2006.02.008",
language = "English",
volume = "69",
pages = "2416--2419",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "16-18",

}

TY - JOUR

T1 - Non-combinatorial estimation of independent autoregressive sources

AU - Póczos, Barnabás

AU - Lőrincz, A.

PY - 2006/10

Y1 - 2006/10

N2 - Identification of mixed independent subspaces is thought to suffer from combinatorial explosion of two kinds: the minimization of mutual information between the estimated subspaces and the search for the optimal number and dimensions of the subspaces. Here we show that independent autoregressive process analysis, under certain conditions, can avoid this problem using a two-phase estimation process. We illustrate the solution by computer demonstration.

AB - Identification of mixed independent subspaces is thought to suffer from combinatorial explosion of two kinds: the minimization of mutual information between the estimated subspaces and the search for the optimal number and dimensions of the subspaces. Here we show that independent autoregressive process analysis, under certain conditions, can avoid this problem using a two-phase estimation process. We illustrate the solution by computer demonstration.

KW - Autoregressive process

KW - Combinatorial explosion

KW - Independent component analysis

UR - http://www.scopus.com/inward/record.url?scp=33748430475&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748430475&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2006.02.008

DO - 10.1016/j.neucom.2006.02.008

M3 - Article

AN - SCOPUS:33748430475

VL - 69

SP - 2416

EP - 2419

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 16-18

ER -