Staff View: Switched neural networks for simultaneous learning of multiple functions.

Switched neural networks for simultaneous learning of multiple functions.

This paper introduces the notion of switched neural networks for learning multiple functions under different switching configurations. The neural network structure has adjustable parameters and for each function the state of the parameter vector is determined by a mask vector, 1/0 for active/inactiv...

Full description

Saved in:

Bibliographic Details
Main Authors:	Önder Efe, Mehmet, Kürkçü, Burak, Kasnakoǧlu, Coşku, Mohamed, Zaharuddin, Zhijie, Liu
Format:	Article
Published:	Institute of Electrical and Electronics Engineers Inc. 2024
Subjects:	TK Electrical engineering. Electronics Nuclear engineering
Online Access:	http://eprints.utm.my/108868/ http://dx.doi.org/10.1109/TETCI.2024.3369981
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.utm.108868
record_format	eprints
spelling	my.utm.1088682025-01-07T08:35:05Z http://eprints.utm.my/108868/ Switched neural networks for simultaneous learning of multiple functions. Önder Efe, Mehmet Kürkçü, Burak Kasnakoǧlu, Coşku Mohamed, Zaharuddin Zhijie, Liu TK Electrical engineering. Electronics Nuclear engineering This paper introduces the notion of switched neural networks for learning multiple functions under different switching configurations. The neural network structure has adjustable parameters and for each function the state of the parameter vector is determined by a mask vector, 1/0 for active/inactive or +1/-1 for plain/inverted. The optimization problem is to schedule the switching strategy (mask vector) required for each function together with the best parameter vector (weights/biases) minimizing the loss function. This requires a procedure that optimizes a vector containing real and binary values simultaneously to discover commonalities among various functions. Our studies show that a small sized neural network structure with an appropriate switching regime is able to learn multiple functions successfully. During the tests focusing on classification, we considered 2-variable binary functions and all 16 combinations have been chosen as the functions. The regression tests consider four functions of two variables. Our studies showed that simple NN structures are capable of storing multiple information via appropriate switching. Institute of Electrical and Electronics Engineers Inc. 2024-03-11 Article PeerReviewed Önder Efe, Mehmet and Kürkçü, Burak and Kasnakoǧlu, Coşku and Mohamed, Zaharuddin and Zhijie, Liu (2024) Switched neural networks for simultaneous learning of multiple functions. IEEE Transactions on Emerging Topics in Computational Intelligence, 8 (4). pp. 3095-3104. ISSN 2471-285X http://dx.doi.org/10.1109/TETCI.2024.3369981 DOI:10.1109/TETCI.2024.3369981
institution	Universiti Teknologi Malaysia
building	UTM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Teknologi Malaysia
content_source	UTM Institutional Repository
url_provider	http://eprints.utm.my/
topic	TK Electrical engineering. Electronics Nuclear engineering
spellingShingle	TK Electrical engineering. Electronics Nuclear engineering Önder Efe, Mehmet Kürkçü, Burak Kasnakoǧlu, Coşku Mohamed, Zaharuddin Zhijie, Liu Switched neural networks for simultaneous learning of multiple functions.
description	This paper introduces the notion of switched neural networks for learning multiple functions under different switching configurations. The neural network structure has adjustable parameters and for each function the state of the parameter vector is determined by a mask vector, 1/0 for active/inactive or +1/-1 for plain/inverted. The optimization problem is to schedule the switching strategy (mask vector) required for each function together with the best parameter vector (weights/biases) minimizing the loss function. This requires a procedure that optimizes a vector containing real and binary values simultaneously to discover commonalities among various functions. Our studies show that a small sized neural network structure with an appropriate switching regime is able to learn multiple functions successfully. During the tests focusing on classification, we considered 2-variable binary functions and all 16 combinations have been chosen as the functions. The regression tests consider four functions of two variables. Our studies showed that simple NN structures are capable of storing multiple information via appropriate switching.
format	Article
author	Önder Efe, Mehmet Kürkçü, Burak Kasnakoǧlu, Coşku Mohamed, Zaharuddin Zhijie, Liu
author_facet	Önder Efe, Mehmet Kürkçü, Burak Kasnakoǧlu, Coşku Mohamed, Zaharuddin Zhijie, Liu
author_sort	Önder Efe, Mehmet
title	Switched neural networks for simultaneous learning of multiple functions.
title_short	Switched neural networks for simultaneous learning of multiple functions.
title_full	Switched neural networks for simultaneous learning of multiple functions.
title_fullStr	Switched neural networks for simultaneous learning of multiple functions.
title_full_unstemmed	Switched neural networks for simultaneous learning of multiple functions.
title_sort	switched neural networks for simultaneous learning of multiple functions.
publisher	Institute of Electrical and Electronics Engineers Inc.
publishDate	2024
url	http://eprints.utm.my/108868/ http://dx.doi.org/10.1109/TETCI.2024.3369981
_version_	1821001617010327552
score	13.244109

Switched neural networks for simultaneous learning of multiple functions.

Similar Items