{"_links":{"self":{"href":"/api/v2/datasets/doi%3A10.5061%2Fdryad.8w9ghx3vx"},"stash:versions":{"href":"/api/v2/datasets/doi%3A10.5061%2Fdryad.8w9ghx3vx/versions"},"stash:version":{"href":"/api/v2/versions/302435"},"stash:download":{"href":"/api/v2/datasets/doi%3A10.5061%2Fdryad.8w9ghx3vx/download"},"curies":[{"name":"stash","href":"https://github.com/datadryad/dryad-app/blob/main/documentation/apis/link_relations.md#{rel}","templated":"true"}]},"identifier":"doi:10.5061/dryad.8w9ghx3vx","id":135026,"storageSize":15759806,"relatedPublicationISSN":"0027-8424","title":"Data from: Machine learning without a processor: Emergent learning in a nonlinear analog network","authors":[{"firstName":"Sam","lastName":"Dillavou","email":"dillavou@sas.upenn.edu","affiliation":"University of Pennsylvania","affiliationROR":"https://ror.org/00b30xv10","affiliations":[{"organization":"University of Pennsylvania","identifier":"https://ror.org/00b30xv10"}],"orcid":"0000-0001-9842-9582"},{"firstName":"Benjamin","lastName":"Beyer","email":"","affiliation":"University of Pennsylvania","affiliationROR":"https://ror.org/00b30xv10","affiliations":[{"organization":"University of Pennsylvania","identifier":"https://ror.org/00b30xv10"}],"order":1},{"firstName":"Menachem","lastName":"Stern","email":"","affiliation":"University of Pennsylvania","affiliationROR":"https://ror.org/00b30xv10","affiliations":[{"organization":"University of Pennsylvania","identifier":"https://ror.org/00b30xv10"}],"order":2},{"firstName":"Andrea","lastName":"Liu","email":"","affiliation":"University of Pennsylvania","affiliationROR":"https://ror.org/00b30xv10","affiliations":[{"organization":"University of Pennsylvania","identifier":"https://ror.org/00b30xv10"}],"order":3},{"firstName":"Marc","lastName":"Miskin","email":"","affiliation":"University of Pennsylvania","affiliationROR":"https://ror.org/00b30xv10","affiliations":[{"organization":"University of Pennsylvania","identifier":"https://ror.org/00b30xv10"}],"order":4},{"firstName":"Douglas","lastName":"Durian","email":"","affiliation":"University of Pennsylvania","affiliationROR":"https://ror.org/00b30xv10","affiliations":[{"organization":"University of Pennsylvania","identifier":"https://ror.org/00b30xv10"}],"order":5}],"abstract":"\u003cp\u003eThe capabilities of digital artificial neural networks grow rapidly with their size, however the time and energy required to train them does as well. The tradeoff is far better for Brains, where the constituent parts (neurons) update their analog connections in ignorance of the actions of other neurons, eschewing centralized processing. Recently introduced analog electronic \u003cem\u003econtrastive local learning networks \u003c/em\u003e(CLLNs) share this important decentralized property. However their capabilities were limited because existing implementations are linear. In this dataset we include experimental demonstrations of a nonlinear CLLN, establishing a new paradigm for scalable learning. Included here are data and scripts required to generate figures 2-6 of the manuscript titled \"Machine learning without a processor: Emergent learning in a nonlinear analog network\".\u003c/p\u003e","funders":[{"organization":"U.S. National Science Foundation","identifierType":"ror","identifier":"https://ror.org/021nxhr62","awardNumber":"MRSEC/DMR-1720530","awardDescription":"","order":0},{"organization":"U.S. National Science Foundation","identifierType":"ror","identifier":"https://ror.org/021nxhr62","awardNumber":"MRSEC/DMR-2309043","awardDescription":"","order":1},{"organization":"U.S. National Science Foundation","identifierType":"ror","identifier":"https://ror.org/021nxhr62","awardNumber":"DMR-2005749","awardDescription":"","order":2},{"organization":"Simons Foundation","identifierType":"ror","identifier":"https://ror.org/01cmst727","awardNumber":"327939","awardDescription":"","order":3},{"organization":"United States Department of Energy","identifierType":"ror","identifier":"https://ror.org/01bj3aw27","awardNumber":"DE-SC0020963","awardDescription":"Division of Materials Sciences and Engineering","order":4},{"organization":"University of Pennsylvania","identifierType":"ror","identifier":"https://ror.org/00b30xv10","awardNumber":"","awardDescription":"Data Driven Discovery Initiative","order":5},{"organization":"David and Lucile Packard Foundation","identifierType":"ror","identifier":"https://ror.org/032atxq54","awardNumber":"","awardDescription":"","order":6}],"keywords":["Physical Learning","emergent learning","soft matter","Active matter","neuromorphic computing","Machine learning"],"fieldOfScience":"Physical sciences","methods":"\u003cp\u003eMethods are described in detail the associated manuscript.\u003c/p\u003e","relatedWorks":[{"relationship":"preprint","identifierType":"URL","identifier":"https://arxiv.org/abs/2311.00537"},{"relationship":"software","identifierType":"DOI","identifier":"https://doi.org/10.5281/zenodo.12009234"},{"relationship":"primary_article","identifierType":"DOI","identifier":"https://doi.org/10.1073/pnas.2319718121"}],"versionNumber":4,"versionStatus":"submitted","curationStatus":"Published","versionChanges":"files_changed","publicationDate":"2024-07-02","lastModificationDate":"2024-07-02","visibility":"public","sharingLink":"http://datadryad.org/dataset/doi:10.5061/dryad.8w9ghx3vx","changedFields":["abstract","related_identifiers",[{"index":2,"id":"https://doi.org/10.1073/pnas.2319718121","type":"primary_article","relation":"iscitedby"}],"data_files"],"license":"https://spdx.org/licenses/CC0-1.0.html","metrics":{"views":66,"downloads":16,"citations":1}}