The University of Southampton
University of Southampton Institutional Repository

Matrix analysis for fast learning of neural networks with application to the classification of acoustic spectra

Matrix analysis for fast learning of neural networks with application to the classification of acoustic spectra
Matrix analysis for fast learning of neural networks with application to the classification of acoustic spectra
Neural networks are increasingly being applied to problems in acoustics and audio signal processing. Large audio data sets are being generated for use in training machine learning algorithms and the reduction of training times is of increasing relevance. The work presented here begins by reformulating the analysis of the classical multilayer perceptron (MLP) to show the explicit dependence of network parameters on the properties of the weight matrices in the network. This analysis then allows the application of the singular value decomposition (SVD) to the weight matrices. An algorithm is presented which makes use of regular applications of the SVD to progressively reduce the dimensionality of the network. This results in significant reductions in network training times of up to 50 percent with very little or no loss in accuracy. The use of the algorithm is demonstrated by applying it to a number of acoustical classification problems that help quantify the extent to which closely related spectra can be distinguished by machine learning.
0001-4966
Paul, Vlad Stefan
a643f880-7e70-4ae0-a27b-4e77c3c451de
Nelson, Philip
5c6f5cc9-ea52-4fe2-9edf-05d696b0c1a9
Paul, Vlad Stefan
a643f880-7e70-4ae0-a27b-4e77c3c451de
Nelson, Philip
5c6f5cc9-ea52-4fe2-9edf-05d696b0c1a9

Paul, Vlad Stefan and Nelson, Philip (2021) Matrix analysis for fast learning of neural networks with application to the classification of acoustic spectra. The Journal of The Acoustical Society of America, 149. (doi:10.1121/10.0005126).

Record type: Article

Abstract

Neural networks are increasingly being applied to problems in acoustics and audio signal processing. Large audio data sets are being generated for use in training machine learning algorithms and the reduction of training times is of increasing relevance. The work presented here begins by reformulating the analysis of the classical multilayer perceptron (MLP) to show the explicit dependence of network parameters on the properties of the weight matrices in the network. This analysis then allows the application of the singular value decomposition (SVD) to the weight matrices. An algorithm is presented which makes use of regular applications of the SVD to progressively reduce the dimensionality of the network. This results in significant reductions in network training times of up to 50 percent with very little or no loss in accuracy. The use of the algorithm is demonstrated by applying it to a number of acoustical classification problems that help quantify the extent to which closely related spectra can be distinguished by machine learning.

Text
Matrix analysis for fast learning - Accepted Manuscript
Restricted to Repository staff only until 14 December 2021.
Request a copy

More information

Accepted/In Press date: 11 May 2021
e-pub ahead of print date: 14 June 2021

Identifiers

Local EPrints ID: 450284
URI: http://eprints.soton.ac.uk/id/eprint/450284
ISSN: 0001-4966
PURE UUID: 1f8241d7-7e1f-40ca-895a-3797966d6826
ORCID for Vlad Stefan Paul: ORCID iD orcid.org/0000-0002-5562-6102

Catalogue record

Date deposited: 20 Jul 2021 16:32
Last modified: 21 Jul 2021 02:02

Export record

Altmetrics

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×