Open Access System for Information Sharing

Login Library

 

Article
Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads
Full metadata record
Files in This Item:
There are no files associated with this item.
DC FieldValueLanguage
dc.contributor.authorHwanjo Yu-
dc.contributor.authorSeongbo Jang-
dc.contributor.authorYe-Eun Jang-
dc.contributor.authorYoung-Jin Kim-
dc.date.available2020-02-11T05:50:09Z-
dc.date.created2020-02-05-
dc.date.issued2020-05-
dc.identifier.issn0020-0255-
dc.identifier.urihttp://oasis.postech.ac.kr/handle/2014.oak/100876-
dc.description.abstractInversion of neural networks aims to find optimal input variables given a target output, and is widely applicable in an industrial field such as optimizing control variables of complex systems in manufacturing facilities. To achieve optimal inputs using a standard first-order optimization technique, proper initialization of input variables is essential. This paper presents a new initialization method for input variables of neural networks based on k-nearest neighbor (k-NN) approach. The proposed method finds inputs which resulted in an output close to a target output in a training dataset, and combine them to form initial input variables. Experiments on a toy dataset demonstrate that our method outperforms random initialization. Also, we introduce an exhaustive case study on power scheduling of a heating, ventilation, and air conditioning (HVAC) system in a building to support the effectiveness of the algorithm.-
dc.languageEnglish-
dc.publisherElsevier-
dc.titleInput Initialization for Inversion of Neural Networks Using k-Nearest Neighbor Approach-
dc.typeArticle-
dc.type.rimsART-
dc.identifier.bibliographicCitationInformation Sciences , v.519, pp.229 - 242-
dc.identifier.wosid미등재-
dc.citation.endPage242-
dc.citation.startPage229-
dc.citation.titleInformation Sciences-
dc.citation.volume519-
dc.contributor.affiliatedAuthorHwanjo Yu-
dc.contributor.affiliatedAuthorSeongbo Jang-
dc.contributor.affiliatedAuthorYe-Eun Jang-
dc.contributor.affiliatedAuthorYoung-Jin Kim-
dc.description.journalClass1-
dc.description.isOpenAccessN-
dc.type.docTypeArticle-

qr_code

  • mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher

 YU, HWANJO
Dept of Computer Science & Enginrg
Read more

Views & Downloads

Browse