File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Machine learning for inverse lithography: Using stochastic gradient descent for robust photomask synthesis

TitleMachine learning for inverse lithography: Using stochastic gradient descent for robust photomask synthesis
Authors
KeywordsInverse imaging
Lithography
Machine learning
Optical
Proximity correction
Robustness
Stochastic gradient descent
Issue Date2010
PublisherInstitute of Physics Publishing. The Journal's web site is located at http://www.iop.org/Journals/jopa
Citation
Journal Of Optics A: Pure And Applied Optics, 2010, v. 12 n. 4, article no. 045601 How to Cite?
AbstractInverse lithography technology (ILT) synthesizes photomasks by solving an inverse imaging problem through optimization of an appropriate functional. Much effort on ILT is dedicated to deriving superior masks at a nominal process condition. However, the lower k1 factor causes the mask to be more sensitive to process variations. Robustness to major process variations, such as focus and dose variations, is desired. In this paper, we consider the focus variation as a stochastic variable, and treat the mask design as a machine learning problem. The stochastic gradient descent approach, which is a useful tool in machine learning, is adopted to train the mask design. Compared with previous work, simulation shows that the proposed algorithm is effective in producing robust masks. © 2010 IOP Publishing Ltd.
Persistent Identifierhttp://hdl.handle.net/10722/124679
ISSN
2011 Impact Factor: 1.924
ISI Accession Number ID
Funding AgencyGrant Number
Hong Kong Special Administrative Region, China7139/06E
7134/08E
Funding Information:

This work was supported in part by the Research Grants Council of the Hong Kong Special Administrative Region, China, under Projects HKU 7139/06E and 7134/08E, and by the UGC Areas of Excellence project Theory, Modeling, and Simulation of Emerging Electronics.

References

 

DC FieldValueLanguage
dc.contributor.authorJia, Nen_HK
dc.contributor.authorLam, EYen_HK
dc.date.accessioned2010-10-31T10:48:05Z-
dc.date.available2010-10-31T10:48:05Z-
dc.date.issued2010en_HK
dc.identifier.citationJournal Of Optics A: Pure And Applied Optics, 2010, v. 12 n. 4, article no. 045601en_HK
dc.identifier.issn1464-4258en_HK
dc.identifier.urihttp://hdl.handle.net/10722/124679-
dc.description.abstractInverse lithography technology (ILT) synthesizes photomasks by solving an inverse imaging problem through optimization of an appropriate functional. Much effort on ILT is dedicated to deriving superior masks at a nominal process condition. However, the lower k1 factor causes the mask to be more sensitive to process variations. Robustness to major process variations, such as focus and dose variations, is desired. In this paper, we consider the focus variation as a stochastic variable, and treat the mask design as a machine learning problem. The stochastic gradient descent approach, which is a useful tool in machine learning, is adopted to train the mask design. Compared with previous work, simulation shows that the proposed algorithm is effective in producing robust masks. © 2010 IOP Publishing Ltd.en_HK
dc.languageengen_HK
dc.publisherInstitute of Physics Publishing. The Journal's web site is located at http://www.iop.org/Journals/jopaen_HK
dc.relation.ispartofJournal of Optics A: Pure and Applied Opticsen_HK
dc.subjectInverse imagingen_HK
dc.subjectLithographyen_HK
dc.subjectMachine learningen_HK
dc.subjectOpticalen_HK
dc.subjectProximity correctionen_HK
dc.subjectRobustnessen_HK
dc.subjectStochastic gradient descenten_HK
dc.titleMachine learning for inverse lithography: Using stochastic gradient descent for robust photomask synthesisen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=2040-8978&volume=12&spage=045601&epage=&date=2010&atitle=Machine+learning+for+inverse+lithography:+Using+stochastic+gradient+descent+for+robust+photomask+synthesisen_HK
dc.identifier.emailLam, EY:elam@eee.hku.hken_HK
dc.identifier.authorityLam, EY=rp00131en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1088/2040-8978/12/4/045601en_HK
dc.identifier.scopuseid_2-s2.0-77950573189en_HK
dc.identifier.hkuros171685en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-77950573189&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume12en_HK
dc.identifier.issue4en_HK
dc.identifier.spage045601en_HK
dc.identifier.spagearticle no. 045601-
dc.identifier.epagearticle no. 045601-
dc.identifier.isiWOS:000279943300016-
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridJia, N=34872289800en_HK
dc.identifier.scopusauthoridLam, EY=7102890004en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats