Application of the minimum fuel neural network to music signals

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

3 Citations (Scopus)

Abstract

Finding an optimal representation of a signal in an over-complete dictionary is often quite difficult. Since general results in this field are not very application friendly it truly helps to specify the framework as much as possible. We investigate the method Minimum Fuel Neural Network (MFNN) for finding sparse representations of music signals. This method is a set of two ordinary differential equations. We argue that the most important parameter for optimal use of this method is the discretization step size, and we demonstrate that this can be a priori determined. This significantly speeds up the convergence of the MFNN to the optimal sparse solution.
Original languageDanish
Title of host publicationProceedings of IEEE International Conference on Accoustics, Speech and Signal Processing
Number of pages4
Volume4
Publication date2004
Pages301-304
Publication statusPublished - 2004
EventIEEE International Conference on Acoustics, Speech, and Signal Processing - Montreal, Canada
Duration: 17 May 200421 May 2004

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing
CountryCanada
CityMontreal
Period17/05/200421/05/2004

Cite this

Harbo, A. L-C. (2004). Application of the minimum fuel neural network to music signals. In Proceedings of IEEE International Conference on Accoustics, Speech and Signal Processing (Vol. 4, pp. 301-304)
Harbo, Anders La-Cour. / Application of the minimum fuel neural network to music signals. Proceedings of IEEE International Conference on Accoustics, Speech and Signal Processing. Vol. 4 2004. pp. 301-304
@inproceedings{9d35e1d0372611da8f0e000ea68e967b,
title = "Application of the minimum fuel neural network to music signals",
abstract = "Finding an optimal representation of a signal in an over-complete dictionary is often quite difficult. Since general results in this field are not very application friendly it truly helps to specify the framework as much as possible. We investigate the method Minimum Fuel Neural Network (MFNN) for finding sparse representations of music signals. This method is a set of two ordinary differential equations. We argue that the most important parameter for optimal use of this method is the discretization step size, and we demonstrate that this can be a priori determined. This significantly speeds up the convergence of the MFNN to the optimal sparse solution.",
author = "Harbo, {Anders La-Cour}",
year = "2004",
language = "Dansk",
volume = "4",
pages = "301--304",
booktitle = "Proceedings of IEEE International Conference on Accoustics, Speech and Signal Processing",

}

Harbo, AL-C 2004, Application of the minimum fuel neural network to music signals. in Proceedings of IEEE International Conference on Accoustics, Speech and Signal Processing. vol. 4, pp. 301-304, Montreal, Canada, 17/05/2004.

Application of the minimum fuel neural network to music signals. / Harbo, Anders La-Cour.

Proceedings of IEEE International Conference on Accoustics, Speech and Signal Processing. Vol. 4 2004. p. 301-304.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Application of the minimum fuel neural network to music signals

AU - Harbo, Anders La-Cour

PY - 2004

Y1 - 2004

N2 - Finding an optimal representation of a signal in an over-complete dictionary is often quite difficult. Since general results in this field are not very application friendly it truly helps to specify the framework as much as possible. We investigate the method Minimum Fuel Neural Network (MFNN) for finding sparse representations of music signals. This method is a set of two ordinary differential equations. We argue that the most important parameter for optimal use of this method is the discretization step size, and we demonstrate that this can be a priori determined. This significantly speeds up the convergence of the MFNN to the optimal sparse solution.

AB - Finding an optimal representation of a signal in an over-complete dictionary is often quite difficult. Since general results in this field are not very application friendly it truly helps to specify the framework as much as possible. We investigate the method Minimum Fuel Neural Network (MFNN) for finding sparse representations of music signals. This method is a set of two ordinary differential equations. We argue that the most important parameter for optimal use of this method is the discretization step size, and we demonstrate that this can be a priori determined. This significantly speeds up the convergence of the MFNN to the optimal sparse solution.

M3 - Konferenceartikel i proceeding

VL - 4

SP - 301

EP - 304

BT - Proceedings of IEEE International Conference on Accoustics, Speech and Signal Processing

ER -

Harbo AL-C. Application of the minimum fuel neural network to music signals. In Proceedings of IEEE International Conference on Accoustics, Speech and Signal Processing. Vol. 4. 2004. p. 301-304