Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks

Embedding computation in molecular contexts incompatible with traditional electronics is expected to have wide ranging impact in synthetic biology, medicine, nanofabrication and other fields. A key remaining challenge lies in developing programming paradigms for molecular computation that are well-a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vasic, Marko, Chalk, Cameron, Khurshid, Sarfraz, Soloveichik, David
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Vasic, Marko
Chalk, Cameron
Khurshid, Sarfraz
Soloveichik, David
description Embedding computation in molecular contexts incompatible with traditional electronics is expected to have wide ranging impact in synthetic biology, medicine, nanofabrication and other fields. A key remaining challenge lies in developing programming paradigms for molecular computation that are well-aligned with the underlying chemical hardware and do not attempt to shoehorn ill-fitting electronics paradigms. We discover a surprisingly tight connection between a popular class of neural networks (binary-weight ReLU aka BinaryConnect) and a class of coupled chemical reactions that are absolutely robust to reaction rates. The robustness of rate-independent chemical computation makes it a promising target for bioengineering implementation. We show how a BinaryConnect neural network trained in silico using well-founded deep learning optimization techniques, can be compiled to an equivalent chemical reaction network, providing a novel molecular programming paradigm. We illustrate such translation on the paradigmatic IRIS and MNIST datasets. Toward intended applications of chemical computation, we further use our method to generate a chemical reaction network that can discriminate between different virus types based on gene expression levels. Our work sets the stage for rich knowledge transfer between neural network and molecular programming communities.
doi_str_mv 10.48550/arxiv.2003.13720
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2003_13720</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2003_13720</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-ad66233ed8bc37511667088ea8ed850d22a3f4b515240835b8bd0963cc5876573</originalsourceid><addsrcrecordid>eNotj8tOg0AYhWfjwlQfwJXzAuBcmIvuar01QWpMjYkb8gM_OJEBMqVe3l7Erk7y5eTkfISccRYnVil2AeHbfcaCMRlzaQQ7Jm83iAN97Fss9y0E-hT6JoD3rmuu6JJmMO4DtHTthxY9diOMru9oX9Nr10H4iV7RNe8jfcb0hWY4dzMcv_rwsTshRzW0Ozw95IJs7263q4co3dyvV8s0Am1YBJXWQkqsbFFKozjXE7UWwU5IsUoIkHVSKK5EwqxUhS0qdqllWSprtDJyQc7_Z2e5fAjOT8fyP8l8lpS_JmpLxQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks</title><source>arXiv.org</source><creator>Vasic, Marko ; Chalk, Cameron ; Khurshid, Sarfraz ; Soloveichik, David</creator><creatorcontrib>Vasic, Marko ; Chalk, Cameron ; Khurshid, Sarfraz ; Soloveichik, David</creatorcontrib><description>Embedding computation in molecular contexts incompatible with traditional electronics is expected to have wide ranging impact in synthetic biology, medicine, nanofabrication and other fields. A key remaining challenge lies in developing programming paradigms for molecular computation that are well-aligned with the underlying chemical hardware and do not attempt to shoehorn ill-fitting electronics paradigms. We discover a surprisingly tight connection between a popular class of neural networks (binary-weight ReLU aka BinaryConnect) and a class of coupled chemical reactions that are absolutely robust to reaction rates. The robustness of rate-independent chemical computation makes it a promising target for bioengineering implementation. We show how a BinaryConnect neural network trained in silico using well-founded deep learning optimization techniques, can be compiled to an equivalent chemical reaction network, providing a novel molecular programming paradigm. We illustrate such translation on the paradigmatic IRIS and MNIST datasets. Toward intended applications of chemical computation, we further use our method to generate a chemical reaction network that can discriminate between different virus types based on gene expression levels. Our work sets the stage for rich knowledge transfer between neural network and molecular programming communities.</description><identifier>DOI: 10.48550/arxiv.2003.13720</identifier><language>eng</language><subject>Computer Science - Emerging Technologies ; Computer Science - Learning ; Computer Science - Neural and Evolutionary Computing</subject><creationdate>2020-03</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2003.13720$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2003.13720$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Vasic, Marko</creatorcontrib><creatorcontrib>Chalk, Cameron</creatorcontrib><creatorcontrib>Khurshid, Sarfraz</creatorcontrib><creatorcontrib>Soloveichik, David</creatorcontrib><title>Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks</title><description>Embedding computation in molecular contexts incompatible with traditional electronics is expected to have wide ranging impact in synthetic biology, medicine, nanofabrication and other fields. A key remaining challenge lies in developing programming paradigms for molecular computation that are well-aligned with the underlying chemical hardware and do not attempt to shoehorn ill-fitting electronics paradigms. We discover a surprisingly tight connection between a popular class of neural networks (binary-weight ReLU aka BinaryConnect) and a class of coupled chemical reactions that are absolutely robust to reaction rates. The robustness of rate-independent chemical computation makes it a promising target for bioengineering implementation. We show how a BinaryConnect neural network trained in silico using well-founded deep learning optimization techniques, can be compiled to an equivalent chemical reaction network, providing a novel molecular programming paradigm. We illustrate such translation on the paradigmatic IRIS and MNIST datasets. Toward intended applications of chemical computation, we further use our method to generate a chemical reaction network that can discriminate between different virus types based on gene expression levels. Our work sets the stage for rich knowledge transfer between neural network and molecular programming communities.</description><subject>Computer Science - Emerging Technologies</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Neural and Evolutionary Computing</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOg0AYhWfjwlQfwJXzAuBcmIvuar01QWpMjYkb8gM_OJEBMqVe3l7Erk7y5eTkfISccRYnVil2AeHbfcaCMRlzaQQ7Jm83iAN97Fss9y0E-hT6JoD3rmuu6JJmMO4DtHTthxY9diOMru9oX9Nr10H4iV7RNe8jfcb0hWY4dzMcv_rwsTshRzW0Ozw95IJs7263q4co3dyvV8s0Am1YBJXWQkqsbFFKozjXE7UWwU5IsUoIkHVSKK5EwqxUhS0qdqllWSprtDJyQc7_Z2e5fAjOT8fyP8l8lpS_JmpLxQ</recordid><startdate>20200330</startdate><enddate>20200330</enddate><creator>Vasic, Marko</creator><creator>Chalk, Cameron</creator><creator>Khurshid, Sarfraz</creator><creator>Soloveichik, David</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200330</creationdate><title>Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks</title><author>Vasic, Marko ; Chalk, Cameron ; Khurshid, Sarfraz ; Soloveichik, David</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-ad66233ed8bc37511667088ea8ed850d22a3f4b515240835b8bd0963cc5876573</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Emerging Technologies</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Neural and Evolutionary Computing</topic><toplevel>online_resources</toplevel><creatorcontrib>Vasic, Marko</creatorcontrib><creatorcontrib>Chalk, Cameron</creatorcontrib><creatorcontrib>Khurshid, Sarfraz</creatorcontrib><creatorcontrib>Soloveichik, David</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Vasic, Marko</au><au>Chalk, Cameron</au><au>Khurshid, Sarfraz</au><au>Soloveichik, David</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks</atitle><date>2020-03-30</date><risdate>2020</risdate><abstract>Embedding computation in molecular contexts incompatible with traditional electronics is expected to have wide ranging impact in synthetic biology, medicine, nanofabrication and other fields. A key remaining challenge lies in developing programming paradigms for molecular computation that are well-aligned with the underlying chemical hardware and do not attempt to shoehorn ill-fitting electronics paradigms. We discover a surprisingly tight connection between a popular class of neural networks (binary-weight ReLU aka BinaryConnect) and a class of coupled chemical reactions that are absolutely robust to reaction rates. The robustness of rate-independent chemical computation makes it a promising target for bioengineering implementation. We show how a BinaryConnect neural network trained in silico using well-founded deep learning optimization techniques, can be compiled to an equivalent chemical reaction network, providing a novel molecular programming paradigm. We illustrate such translation on the paradigmatic IRIS and MNIST datasets. Toward intended applications of chemical computation, we further use our method to generate a chemical reaction network that can discriminate between different virus types based on gene expression levels. Our work sets the stage for rich knowledge transfer between neural network and molecular programming communities.</abstract><doi>10.48550/arxiv.2003.13720</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2003.13720
ispartof
issn
language eng
recordid cdi_arxiv_primary_2003_13720
source arXiv.org
subjects Computer Science - Emerging Technologies
Computer Science - Learning
Computer Science - Neural and Evolutionary Computing
title Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T01%3A07%3A16IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20Molecular%20Programming:%20A%20Natural%20Implementation%20of%20Binary-Weight%20ReLU%20Neural%20Networks&rft.au=Vasic,%20Marko&rft.date=2020-03-30&rft_id=info:doi/10.48550/arxiv.2003.13720&rft_dat=%3Carxiv_GOX%3E2003_13720%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true