{"id":"https://openalex.org/W3006277650","doi":"https://doi.org/10.1109/icassp40776.2020.9054549","title":"A Neural Network Based on First Principles","display_name":"A Neural Network Based on First Principles","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3006277650","doi":"https://doi.org/10.1109/icassp40776.2020.9054549","mag":"3006277650"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.07469","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013350630","display_name":"Paul M. Baggenstoss","orcid":"https://orcid.org/0000-0002-3739-6104"},"institutions":[{"id":"https://openalex.org/I4210166245","display_name":"Fraunhofer Institute for Communication, Information Processing and Ergonomics","ror":"https://ror.org/05nn0gw40","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210166245","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Paul M Baggenstoss","raw_affiliation_strings":["Fraunhofer FKIE,Wachtberg,Germany,53343"],"affiliations":[{"raw_affiliation_string":"Fraunhofer FKIE,Wachtberg,Germany,53343","institution_ids":["https://openalex.org/I4210166245"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013350630"],"corresponding_institution_ids":["https://openalex.org/I4210166245"],"apc_list":null,"apc_paid":null,"fwci":0.14685955,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51107939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.655876874923706},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6094592213630676},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.6027454733848572},{"id":"https://openalex.org/keywords/conditional-probability-distribution","display_name":"Conditional probability distribution","score":0.544746994972229},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5190392136573792},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5155360698699951},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.5000114440917969},{"id":"https://openalex.org/keywords/conditional-expectation","display_name":"Conditional expectation","score":0.49820923805236816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4796862304210663},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.47933945059776306},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4592340886592865},{"id":"https://openalex.org/keywords/conditional-entropy","display_name":"Conditional entropy","score":0.44830408692359924},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4383796751499176},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4231879711151123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37974289059638977},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3490942120552063},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20598715543746948}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.655876874923706},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6094592213630676},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.6027454733848572},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.544746994972229},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5190392136573792},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5155360698699951},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.5000114440917969},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.49820923805236816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4796862304210663},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.47933945059776306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4592340886592865},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.44830408692359924},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4383796751499176},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4231879711151123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37974289059638977},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3490942120552063},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20598715543746948},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.07469","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.07469","pdf_url":"https://arxiv.org/pdf/2002.07469","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3006277650","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.07469.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:fraunhofer.de:N-614681","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-614681.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer FKIE","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/409483","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/409483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},{"id":"doi:10.48550/arxiv.2002.07469","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.07469","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.17023/yp34-n678","is_oa":true,"landing_page_url":"https://doi.org/10.17023/yp34-n678","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.07469","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.07469","pdf_url":"https://arxiv.org/pdf/2002.07469","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3006277650.pdf","grobid_xml":"https://content.openalex.org/works/W3006277650.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1654590594","https://openalex.org/W1658172446","https://openalex.org/W2018490621","https://openalex.org/W2033491515","https://openalex.org/W2034921015","https://openalex.org/W2109301048","https://openalex.org/W2124914669","https://openalex.org/W2131712117","https://openalex.org/W2142811628","https://openalex.org/W2467604901","https://openalex.org/W2514204487","https://openalex.org/W2557283755","https://openalex.org/W2581803003","https://openalex.org/W2766482344","https://openalex.org/W2767286248","https://openalex.org/W2806370671","https://openalex.org/W2899675781","https://openalex.org/W2905121418","https://openalex.org/W2963074311","https://openalex.org/W2984687478","https://openalex.org/W6636913704","https://openalex.org/W6637242042","https://openalex.org/W6678801095","https://openalex.org/W6689235393","https://openalex.org/W6720208624","https://openalex.org/W6726556055","https://openalex.org/W6746023985","https://openalex.org/W6752518174","https://openalex.org/W6756026151"],"related_works":["https://openalex.org/W2153627206","https://openalex.org/W2323905706","https://openalex.org/W2618706938","https://openalex.org/W2067621428","https://openalex.org/W90809020","https://openalex.org/W2917350050","https://openalex.org/W3011091082","https://openalex.org/W2053462229","https://openalex.org/W1991324520","https://openalex.org/W2919385927","https://openalex.org/W215616351","https://openalex.org/W2201133737","https://openalex.org/W3139119866","https://openalex.org/W2991229825","https://openalex.org/W2144859550","https://openalex.org/W2106560638","https://openalex.org/W3177463154","https://openalex.org/W2132849848","https://openalex.org/W2302053044","https://openalex.org/W3201054025"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,18,53,64,82,122],"Neural":[4],"network":[5,68,120,128],"is":[6,61,103],"derived":[7],"from":[8],"first":[9],"principles,":[10],"assuming":[11],"only":[12],"that":[13,60,90],"each":[14,42],"layer":[15,47],"begins":[16],"with":[17,69,116],"linear":[19,125],"dimension-reducing":[20],"transformation.":[21],"The":[22],"approach":[23],"appeals":[24],"to":[25,32,74],"the":[26,34,38,46,56,92,100,130],"principle":[27],"of":[28,37,41,66,124],"Maximum":[29],"Entropy":[30],"(MaxEnt)":[31],"find":[33],"posterior":[35,51],"distribution":[36,94],"input":[39],"data":[40],"layer,":[43],"conditioned":[44],"on":[45],"output":[48],"variables.":[49],"This":[50,79],"has":[52],"well-defined":[54],"mean,":[55],"conditional":[57,93,96],"mean":[58,97],"estimator,":[59],"calculated":[62],"using":[63],"type":[65,123],"neural":[67],"theoretically-derived":[70],"activation":[71],"functions":[72],"similar":[73],"sigmoid,":[75],"softplus,":[76],"and":[77,95,121],"relu.":[78],"implicitly":[80],"provides":[81],"theoretical":[83],"justification":[84],"for":[85,107],"their":[86],"use.":[87],"A":[88],"theorem":[89],"finds":[91],"estimator":[98],"under":[99],"MaxEnt":[101],"prior":[102],"proposed,":[104],"unifying":[105],"results":[106,112],"special":[108],"cases.":[109],"Combining":[110],"layers":[111],"in":[113,129],"an":[114],"auto-encoder":[115],"conventional":[117],"feed-forward":[118],"analysis":[119],"Bayesian":[126],"belief":[127],"reconstruction":[131],"path.":[132]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}