{"id":487,"date":"2022-09-03T14:18:06","date_gmt":"2022-09-03T18:18:06","guid":{"rendered":"https:\/\/wordpress.cs.vt.edu\/elhamod\/?page_id=487"},"modified":"2022-09-03T14:37:27","modified_gmt":"2022-09-03T18:37:27","slug":"cophy-pgnn-learning-physics-guided-neural-networks-with-competing-loss-functions-for-solving-eigenvalue-problems","status":"publish","type":"page","link":"https:\/\/wordpress.cs.vt.edu\/elhamod\/cophy-pgnn-learning-physics-guided-neural-networks-with-competing-loss-functions-for-solving-eigenvalue-problems\/","title":{"rendered":"CoPhy-PGNN: Learning Physics-guided Neural Networks with Competing Loss Functions for Solving Eigenvalue Problems"},"content":{"rendered":"\n<div class=\"wp-block-media-text alignwide has-media-on-the-right is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"782\" src=\"https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-content\/uploads\/sites\/169\/2022\/09\/cophy-1-1-1024x782.png\" alt=\"\" class=\"wp-image-489 size-full\" srcset=\"https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-content\/uploads\/sites\/169\/2022\/09\/cophy-1-1-1024x782.png 1024w, https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-content\/uploads\/sites\/169\/2022\/09\/cophy-1-1-300x229.png 300w, https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-content\/uploads\/sites\/169\/2022\/09\/cophy-1-1-768x586.png 768w, https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-content\/uploads\/sites\/169\/2022\/09\/cophy-1-1-1536x1173.png 1536w, https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-content\/uploads\/sites\/169\/2022\/09\/cophy-1-1.png 2009w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p>This project investigated a deep learning alternative to the computationally expensive eigen-decomposition numerical solvers. I applied this research to multiple case-studies in physics, namely the Ising model and electromagnetic propagation. I have modified the loss function in the back-propagation algorithm to include physics constraints, thus achieving higher accuracies and a better extrapolation power with low computational complexity. I have also investigated the effect of this modification on the loss surface to explain my method\u2019s advantages.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\" \/>\n\n\n\n<h2 class=\"wp-block-heading\">Publications<\/h2>\n\n\n\n<p><a rel=\"noreferrer noopener\" href=\"https:\/\/dl.acm.org\/doi\/10.1145\/3530911\" data-type=\"URL\" data-id=\"https:\/\/dl.acm.org\/doi\/10.1145\/3530911\" target=\"_blank\">Elhamod, Mohannad et al. &#8220;CoPhy-PGNN: Learning Physics-Guided Neural Networks with Competing Loss Functions for Solving Eigenvalue Problems&#8221;.\u00a0<em>ACM Trans. Intell. Syst. Technol.<\/em>. (2022).<\/a><\/p>\n<\/div><\/div>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":359,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-487","page","type-page","status-publish","hentry"],"jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-json\/wp\/v2\/pages\/487","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-json\/wp\/v2\/users\/359"}],"replies":[{"embeddable":true,"href":"https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-json\/wp\/v2\/comments?post=487"}],"version-history":[{"count":5,"href":"https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-json\/wp\/v2\/pages\/487\/revisions"}],"predecessor-version":[{"id":497,"href":"https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-json\/wp\/v2\/pages\/487\/revisions\/497"}],"wp:attachment":[{"href":"https:\/\/wordpress.cs.vt.edu\/elhamod\/wp-json\/wp\/v2\/media?parent=487"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}