Show simple item record

dc.contributor.authorLiu, J.
dc.contributor.authorLiu, Y.
dc.contributor.authorZhang, Qichun
dc.date.accessioned2022-02-14T12:05:42Z
dc.date.accessioned2022-02-14T15:14:07Z
dc.date.available2022-02-14T12:05:42Z
dc.date.available2022-02-14T15:14:07Z
dc.date.issued2022-04
dc.identifier.citationLiu J, Liu Y & Zhang Q (2022) A weight initialization method based on neural network with asymmetric activation function. Neurocomputing. 483: 171-182.en_US
dc.identifier.urihttp://hdl.handle.net/10454/18746
dc.descriptionYesen_US
dc.description.abstractWeight initialization of neural networks has an important influence on the learning process, and the selection of initial weights is related to the activation interval of the activation function. It is proposed that an improved and extended weight initialization method for neural network with asymmetric activation function as an extension of the linear interval tolerance method (LIT), called ‘GLIT’ (generalized LIT), which is more suitable for higher-dimensional inputs. The purpose is to expand the selection range of the activation function so that the input falls in the unsaturated region, so as to improve the performance of the network. Then, a tolerance solution theorem based upon neural network system is given and proved. Furthermore, the algorithm is given about determining the initial weight interval. The validity of the theorem and algorithm is verified by numerical experiments. The input could fall into any preset interval in the sense of probability under the GLIT method. In another sense, the GLIT method could provide a theoretical basis for the further study of neural networks.en_US
dc.description.sponsorshipThe author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This paper is partly supported by National Science Foundation of China under Grants (62073226, 61603262), Liaoning Province Natural Science Foundation (2020-KF-11-09, 2021-KF-11-05), Shen-Fu Demonstration Zone Science and Technology Plan Project (2020JH13, 2021JH07), Central Government Guides Local Science and Technology Development Funds of Liaoning Province (2021JH6).en_US
dc.language.isoenen_US
dc.rights© 2022 Elsevier. Reproduced in accordance with the publisher's self-archiving policy. This manuscript version is made available under the CC-BY-NC-ND 4.0 license.
dc.subjectWeight initializationen_US
dc.subjectAsymmetric activation functionen_US
dc.subjectInterval linear systemen_US
dc.subjectTolerate solutionen_US
dc.subjectNeural networken_US
dc.titleA weight initialization method based on neural network with asymmetric activation functionen_US
dc.status.refereedYesen_US
dc.date.Accepted2022-01-23
dc.date.application2022-02-01
dc.typeArticleen_US
dc.type.versionAccepted manuscripten_US
dc.identifier.doihttps://doi.org/10.1016/j.neucom.2022.01.088
dc.date.updated2022-02-14T12:05:44Z
refterms.dateFOA2022-02-14T15:14:59Z
dc.openaccess.statusopenAccessen_US


Item file(s)

Thumbnail
Name:
Zhang_Q_2022.pdf
Size:
381.8Kb
Format:
PDF
Description:
Accepted manuscript
Thumbnail
Name:
1-s2.0-S0925231222001138-main.pdf
Size:
431.7Kb
Format:
PDF
Description:
Published version - no permission ...

This item appears in the following Collection(s)

Show simple item record