Electron-nucleus cross sections from transfer learning

Electron-nucleus cross sections from transfer learning

Transfer learning (TL) allows a deep neural network (DNN) trained on one type of data to be adapted for new problems with limited information. We propose to use the TL technique in physics. The DNN learns the physics of one process, and after fine-tuning, it makes predictions for related processes....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-08
Hauptverfasser: Graczyk, Krzysztof M, Kowal, Beata E, Ankowski, Artur M, Banerjee, Rwik Dharmapal, Bonilla, Jose Luis, Prasad, Hemant, Sobczyk, Jan T
Format: Artikel
Sprache:eng
Schlagworte:
Artificial neural networks
Lithium
Machine learning
Scattering cross sections
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Graczyk, Krzysztof M
Kowal, Beata E
Ankowski, Artur M
Banerjee, Rwik Dharmapal
Bonilla, Jose Luis
Prasad, Hemant
Sobczyk, Jan T
description Transfer learning (TL) allows a deep neural network (DNN) trained on one type of data to be adapted for new problems with limited information. We propose to use the TL technique in physics. The DNN learns the physics of one process, and after fine-tuning, it makes predictions for related processes. We consider the DNNs, trained on inclusive electron-carbon scattering data, and show that after fine-tuning, they accurately predict cross sections for electron interactions with nuclear targets ranging from lithium to iron. The method works even when the DNN is fine-tuned on a small dataset.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3095285540</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3095285540</sourcerecordid><originalsourceid>FETCH-proquest_journals_30952855403</originalsourceid><addsrcrecordid>eNqNikEKwjAQAIMgWLR_CHgOxE1T61kqPsB7CSGRlrjR3eT_9uADPA3MzEY0YMxJDR3ATrTMi9Ya-jNYaxrRjyn4QhkVVp9CZekpM0te7ZyRZaT8koUccgwkU3CEMz4PYhtd4tD-uBfH2_i43tWb8qcGLtOSK-GaJqMvFgZrO23-u74khzYQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3095285540</pqid></control><display><type>article</type><title>Electron-nucleus cross sections from transfer learning</title><source>Free E- Journals</source><creator>Graczyk, Krzysztof M ; Kowal, Beata E ; Ankowski, Artur M ; Banerjee, Rwik Dharmapal ; Bonilla, Jose Luis ; Prasad, Hemant ; Sobczyk, Jan T</creator><creatorcontrib>Graczyk, Krzysztof M ; Kowal, Beata E ; Ankowski, Artur M ; Banerjee, Rwik Dharmapal ; Bonilla, Jose Luis ; Prasad, Hemant ; Sobczyk, Jan T</creatorcontrib><description>Transfer learning (TL) allows a deep neural network (DNN) trained on one type of data to be adapted for new problems with limited information. We propose to use the TL technique in physics. The DNN learns the physics of one process, and after fine-tuning, it makes predictions for related processes. We consider the DNNs, trained on inclusive electron-carbon scattering data, and show that after fine-tuning, they accurately predict cross sections for electron interactions with nuclear targets ranging from lithium to iron. The method works even when the DNN is fine-tuned on a small dataset.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Lithium ; Machine learning ; Scattering cross sections</subject><ispartof>arXiv.org, 2024-08</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Graczyk, Krzysztof M</creatorcontrib><creatorcontrib>Kowal, Beata E</creatorcontrib><creatorcontrib>Ankowski, Artur M</creatorcontrib><creatorcontrib>Banerjee, Rwik Dharmapal</creatorcontrib><creatorcontrib>Bonilla, Jose Luis</creatorcontrib><creatorcontrib>Prasad, Hemant</creatorcontrib><creatorcontrib>Sobczyk, Jan T</creatorcontrib><title>Electron-nucleus cross sections from transfer learning</title><title>arXiv.org</title><description>Transfer learning (TL) allows a deep neural network (DNN) trained on one type of data to be adapted for new problems with limited information. We propose to use the TL technique in physics. The DNN learns the physics of one process, and after fine-tuning, it makes predictions for related processes. We consider the DNNs, trained on inclusive electron-carbon scattering data, and show that after fine-tuning, they accurately predict cross sections for electron interactions with nuclear targets ranging from lithium to iron. The method works even when the DNN is fine-tuned on a small dataset.</description><subject>Artificial neural networks</subject><subject>Lithium</subject><subject>Machine learning</subject><subject>Scattering cross sections</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNikEKwjAQAIMgWLR_CHgOxE1T61kqPsB7CSGRlrjR3eT_9uADPA3MzEY0YMxJDR3ATrTMi9Ya-jNYaxrRjyn4QhkVVp9CZekpM0te7ZyRZaT8koUccgwkU3CEMz4PYhtd4tD-uBfH2_i43tWb8qcGLtOSK-GaJqMvFgZrO23-u74khzYQ</recordid><startdate>20240819</startdate><enddate>20240819</enddate><creator>Graczyk, Krzysztof M</creator><creator>Kowal, Beata E</creator><creator>Ankowski, Artur M</creator><creator>Banerjee, Rwik Dharmapal</creator><creator>Bonilla, Jose Luis</creator><creator>Prasad, Hemant</creator><creator>Sobczyk, Jan T</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240819</creationdate><title>Electron-nucleus cross sections from transfer learning</title><author>Graczyk, Krzysztof M ; Kowal, Beata E ; Ankowski, Artur M ; Banerjee, Rwik Dharmapal ; Bonilla, Jose Luis ; Prasad, Hemant ; Sobczyk, Jan T</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_30952855403</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial neural networks</topic><topic>Lithium</topic><topic>Machine learning</topic><topic>Scattering cross sections</topic><toplevel>online_resources</toplevel><creatorcontrib>Graczyk, Krzysztof M</creatorcontrib><creatorcontrib>Kowal, Beata E</creatorcontrib><creatorcontrib>Ankowski, Artur M</creatorcontrib><creatorcontrib>Banerjee, Rwik Dharmapal</creatorcontrib><creatorcontrib>Bonilla, Jose Luis</creatorcontrib><creatorcontrib>Prasad, Hemant</creatorcontrib><creatorcontrib>Sobczyk, Jan T</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Graczyk, Krzysztof M</au><au>Kowal, Beata E</au><au>Ankowski, Artur M</au><au>Banerjee, Rwik Dharmapal</au><au>Bonilla, Jose Luis</au><au>Prasad, Hemant</au><au>Sobczyk, Jan T</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Electron-nucleus cross sections from transfer learning</atitle><jtitle>arXiv.org</jtitle><date>2024-08-19</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Transfer learning (TL) allows a deep neural network (DNN) trained on one type of data to be adapted for new problems with limited information. We propose to use the TL technique in physics. The DNN learns the physics of one process, and after fine-tuning, it makes predictions for related processes. We consider the DNNs, trained on inclusive electron-carbon scattering data, and show that after fine-tuning, they accurately predict cross sections for electron interactions with nuclear targets ranging from lithium to iron. The method works even when the DNN is fine-tuned on a small dataset.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_3095285540
source Free E- Journals
subjects Artificial neural networks
Lithium
Machine learning
Scattering cross sections
title Electron-nucleus cross sections from transfer learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T22%3A16%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Electron-nucleus%20cross%20sections%20from%20transfer%20learning&rft.jtitle=arXiv.org&rft.au=Graczyk,%20Krzysztof%20M&rft.date=2024-08-19&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3095285540%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3095285540&rft_id=info:pmid/&rfr_iscdi=true