Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions

Finding a biologically-relevant inductive bias for training DNNs on large fitness landscapes is challenging. Here, the authors propose a method called Epistatic Net that improves DNN prediction accuracy and interpretation speed by integrating the knowledge that higher-order epistatic interactions ar...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Amirali Aghazadeh, Hunter Nisonoff, Orhan Ocal, David H. Brookes, Yijie Huang, O. Ozan Koyluoglu, Jennifer Listgarten, Kannan Ramchandran
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Science Q
Acceso en línea:	https://doaj.org/article/aaa0481b36da43839b3bcab8d8fbcc3a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:aaa0481b36da43839b3bcab8d8fbcc3a
record_format	dspace
spelling	oai:doaj.org-article:aaa0481b36da43839b3bcab8d8fbcc3a2021-12-02T16:37:39ZEpistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions10.1038/s41467-021-25371-32041-1723https://doaj.org/article/aaa0481b36da43839b3bcab8d8fbcc3a2021-09-01T00:00:00Zhttps://doi.org/10.1038/s41467-021-25371-3https://doaj.org/toc/2041-1723Finding a biologically-relevant inductive bias for training DNNs on large fitness landscapes is challenging. Here, the authors propose a method called Epistatic Net that improves DNN prediction accuracy and interpretation speed by integrating the knowledge that higher-order epistatic interactions are usually sparse.Amirali AghazadehHunter NisonoffOrhan OcalDavid H. BrookesYijie HuangO. Ozan KoyluogluJennifer ListgartenKannan RamchandranNature PortfolioarticleScienceQENNature Communications, Vol 12, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Science Q
spellingShingle	Science Q Amirali Aghazadeh Hunter Nisonoff Orhan Ocal David H. Brookes Yijie Huang O. Ozan Koyluoglu Jennifer Listgarten Kannan Ramchandran Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
description	Finding a biologically-relevant inductive bias for training DNNs on large fitness landscapes is challenging. Here, the authors propose a method called Epistatic Net that improves DNN prediction accuracy and interpretation speed by integrating the knowledge that higher-order epistatic interactions are usually sparse.
format	article
author	Amirali Aghazadeh Hunter Nisonoff Orhan Ocal David H. Brookes Yijie Huang O. Ozan Koyluoglu Jennifer Listgarten Kannan Ramchandran
author_facet	Amirali Aghazadeh Hunter Nisonoff Orhan Ocal David H. Brookes Yijie Huang O. Ozan Koyluoglu Jennifer Listgarten Kannan Ramchandran
author_sort	Amirali Aghazadeh
title	Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title_short	Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title_full	Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title_fullStr	Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title_full_unstemmed	Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
title_sort	epistatic net allows the sparse spectral regularization of deep neural networks for inferring fitness functions
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/aaa0481b36da43839b3bcab8d8fbcc3a
work_keys_str_mv	AT amiraliaghazadeh epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions AT hunternisonoff epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions AT orhanocal epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions AT davidhbrookes epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions AT yijiehuang epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions AT oozankoyluoglu epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions AT jenniferlistgarten epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions AT kannanramchandran epistaticnetallowsthesparsespectralregularizationofdeepneuralnetworksforinferringfitnessfunctions
_version_	1718383650219753472

Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions

Ejemplares similares