Efficient design of neural networks for the classification of acoustic spectra
Efficient design of neural networks for the classification of acoustic spectra
A previous paper by Paul and Nelson [(2021). J. Acoust. Soc. Am. 149(6), 4119-4133] presented the application of the singular value decomposition (SVD) to the weight matrices of multilayer perceptron (MLP) networks as a pruning strategy to remove weight parameters. This work builds on the previous technique and presents a method of reducing the size of a hidden layer by applying a similar SVD algorithm. Results show that by reducing the neurons in the hidden layer, a significant amount of training time is saved compared to the algorithm presented in the previous paper while no or little accuracy is being lost compared to the original MLP model.
Paul, Vlad S.
a643f880-7e70-4ae0-a27b-4e77c3c451de
Nelson, Philip A.
5c6f5cc9-ea52-4fe2-9edf-05d696b0c1a9
15 September 2023
Paul, Vlad S.
a643f880-7e70-4ae0-a27b-4e77c3c451de
Nelson, Philip A.
5c6f5cc9-ea52-4fe2-9edf-05d696b0c1a9
Paul, Vlad S. and Nelson, Philip A.
(2023)
Efficient design of neural networks for the classification of acoustic spectra.
JASA Express Letters, 3 (9), [094802].
(doi:10.1121/10.0020990).
Abstract
A previous paper by Paul and Nelson [(2021). J. Acoust. Soc. Am. 149(6), 4119-4133] presented the application of the singular value decomposition (SVD) to the weight matrices of multilayer perceptron (MLP) networks as a pruning strategy to remove weight parameters. This work builds on the previous technique and presents a method of reducing the size of a hidden layer by applying a similar SVD algorithm. Results show that by reducing the neurons in the hidden layer, a significant amount of training time is saved compared to the algorithm presented in the previous paper while no or little accuracy is being lost compared to the original MLP model.
Text
094802_1_10.0020990
- Version of Record
More information
Accepted/In Press date: 28 August 2023
Published date: 15 September 2023
Additional Information:
Funding Information:
This work was supported by the Engineering and Physical Sciences Research Council (EPSRC,UKRI) EP/R513325/1.
Publisher Copyright:
© 2023 Author(s).
Identifiers
Local EPrints ID: 482333
URI: http://eprints.soton.ac.uk/id/eprint/482333
ISSN: 2691-1191
PURE UUID: 790be429-bea7-4609-b274-cae50ad87d0d
Catalogue record
Date deposited: 26 Sep 2023 17:07
Last modified: 18 Mar 2024 03:54
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
