Fast non-negative dimensionality reduction for protein fold recognition
Fast non-negative dimensionality reduction for protein fold recognition
In this paper, dimensionality reduction via matrix factorization with nonnegativity constraints is studied. Because of these constraints, it stands apart from other linear dimensionality reduction methods. Here we explore nonnegative matrix factorization in combination with a classifier for protein fold recognition. Since typically matrix factorization is iteratively done, convergence can be slow. To alleviate this problem, a significantly faster (more than 11 times) algorithm is proposed.
665 - 672
Okun, Oleg
4b9de7d1-ecbe-46a9-84c3-987f1dd611ef
Priisalu, Helen
d89ad2b8-e422-4546-98ac-f45c484de620
Couto Alves, Alexessander
87b9179e-abde-4ca5-abfc-4b7c5ac8b03b
2005
Okun, Oleg
4b9de7d1-ecbe-46a9-84c3-987f1dd611ef
Priisalu, Helen
d89ad2b8-e422-4546-98ac-f45c484de620
Couto Alves, Alexessander
87b9179e-abde-4ca5-abfc-4b7c5ac8b03b
Okun, Oleg, Priisalu, Helen and Couto Alves, Alexessander
(2005)
Fast non-negative dimensionality reduction for protein fold recognition.
In Lecture Notes on Computer Science.
Springer Berlin.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
In this paper, dimensionality reduction via matrix factorization with nonnegativity constraints is studied. Because of these constraints, it stands apart from other linear dimensionality reduction methods. Here we explore nonnegative matrix factorization in combination with a classifier for protein fold recognition. Since typically matrix factorization is iteratively done, convergence can be slow. To alleviate this problem, a significantly faster (more than 11 times) algorithm is proposed.
Text
11564096_67
- Version of Record
Restricted to Repository staff only
Request a copy
More information
Published date: 2005
Venue - Dates:
European Conference on Machine Learning 2015, 2005-01-01
Identifiers
Local EPrints ID: 494830
URI: http://eprints.soton.ac.uk/id/eprint/494830
PURE UUID: 69d97433-120f-4e35-b792-0bcdc8a38e23
Catalogue record
Date deposited: 16 Oct 2024 16:42
Last modified: 17 Oct 2024 02:08
Export record
Contributors
Author:
Oleg Okun
Author:
Helen Priisalu
Author:
Alexessander Couto Alves
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