{"id":"https://openalex.org/W2407024328","doi":null,"title":"Are Rosenblatt multilayer perceptrons more powerfull than sigmoidal multilayer perceptrons? From a counter example to a general result","display_name":"Are Rosenblatt multilayer perceptrons more powerfull than sigmoidal multilayer perceptrons? From a counter example to a general result","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2407024328","mag":"2407024328"},"language":"en","primary_location":{"id":"mag:2407024328","doi":null,"is_oa":false,"landing_page_url":"https://novaresearch.unl.pt/en/publications/are-rosenblatt-multilayer-perceptrons-more-powerfull-than-sigmoid","pdf_url":null,"source":{"id":"https://openalex.org/S4306421047","display_name":"The European Symposium on Artificial Neural Networks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"The European Symposium on Artificial Neural Networks","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071759445","display_name":"Jos\u00e9 Barahona da Fonseca","orcid":"https://orcid.org/0000-0003-0278-5334","observed_orcids":["https://orcid.org/0000-0003-0278-5334"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jos\u00e9 Barahona da Fonseca","raw_affiliation_strings":["DEE2010-C1 Sistemas Digitais e Percepcionais"],"raw_orcid":"https://orcid.org/0000-0003-0278-5334","affiliations":[{"raw_affiliation_string":"DEE2010-C1 Sistemas Digitais e Percepcionais","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5071759445"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4528,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51199845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"345","last_page":"350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T12676","display_name":"Machine Learning and ELM","score":9.999999747378752e-05,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sigmoidal-neural-networks","display_name":"sigmoidal neural networks","score":0.9190000295639038},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"multilayer perceptron","score":0.8939999938011169},{"id":"https://openalex.org/keywords/backpropagation","display_name":"backpropagation","score":0.6669999957084656},{"id":"https://openalex.org/keywords/np-completeness","display_name":"NP-completeness","score":0.7049999833106995},{"id":"https://openalex.org/keywords/computing-power","display_name":"computational power","score":0.49000000953674316},{"id":"https://openalex.org/keywords/classification","display_name":"classification","score":0.44699999690055847},{"id":"https://openalex.org/keywords/threshold-logic-gates","display_name":"threshold gates","score":0.5929999947547913},{"id":"https://openalex.org/keywords/vlsi-design","display_name":"VLSI design","score":0.9079999923706055},{"id":"https://openalex.org/keywords/nanotechnology","display_name":"nanotechnology","score":0.8939999938011169}],"concepts":[{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.8842427134513855},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.8838475942611694},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.7837373614311218},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6994573473930359},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6798856258392334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5215032696723938},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.5048090219497681},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5018219947814941},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.4596426486968994},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45286059379577637},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.4411669671535492},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11816129088401794},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.07876655459403992}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2407024328","doi":null,"is_oa":false,"landing_page_url":"https://novaresearch.unl.pt/en/publications/are-rosenblatt-multilayer-perceptrons-more-powerfull-than-sigmoid","pdf_url":null,"source":{"id":"https://openalex.org/S4306421047","display_name":"The European Symposium on Artificial Neural Networks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"The European Symposium on Artificial Neural Networks","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1484418787","https://openalex.org/W1491596324","https://openalex.org/W1498436455","https://openalex.org/W1975092632","https://openalex.org/W1995341919","https://openalex.org/W2040870580","https://openalex.org/W2046952831","https://openalex.org/W2052534572","https://openalex.org/W2068701221","https://openalex.org/W2084081789","https://openalex.org/W2099982883","https://openalex.org/W2118690660","https://openalex.org/W2126902546","https://openalex.org/W2134063109","https://openalex.org/W2322002063","https://openalex.org/W2504871398","https://openalex.org/W4237060324"],"related_works":["https://openalex.org/W2293121926","https://openalex.org/W7097117899","https://openalex.org/W2134371255","https://openalex.org/W2164348255","https://openalex.org/W2071255734","https://openalex.org/W2164327370","https://openalex.org/W1546709148","https://openalex.org/W2159373453","https://openalex.org/W2100595623","https://openalex.org/W7009080426"],"abstract_inverted_index":{"In":[0,48],"the":[1,3,6,97,104,130,144],"eighties":[2],"problem":[4,154],"of":[5,8,60,64,106,129],"lack":[7],"an":[9,32,116,147],"efficient":[10,33,148],"algorithm":[11,34],"to":[12,30,35,132,150,206],"train":[13,36],"multilayer":[14,37,138,175,188,193],"Rosenblatt":[15,72],"perceptrons":[16,114,176,195],"was":[17],"solved":[18],"by":[19,62,94],"sigmoidal":[20,84,189],"neural":[21,88,190],"networks":[22],"and":[23,123,125,141],"backpropagation.":[24],"But":[25],"should":[26],"we":[27,51,126,142,170,177,183,196,204],"still":[28],"try":[29],"find":[31],"hardlimit":[38,113,139,162,174,194],"neuronal":[39],"networks,":[40,191],"a":[41,45,58,65,69,83,137,159,165,209],"task":[42],"known":[43],"as":[44,164,182,203],"NP-Complete":[46],"problem?":[47],"this":[49,54],"work":[50],"show":[52,102],"that":[53,172],"would":[55],"not":[56],"be":[57],"waste":[59],"time":[61],"means":[63],"counter":[66],"example":[67],"where":[68],"two":[70,86,160],"layer":[71,87,161],"perceptron":[73,140,163],"with":[74,90,109,136,155,158,173,187,192],"21":[75],"neurons":[76,92],"showed":[77],"much":[78],"more":[79],"computational":[80],"power":[81],"than":[82],"feedforward":[85],"network":[89],"300":[91],"trained":[93],"backpropagation":[95],"for":[96,146],"same":[98],"classification":[99,153,201],"problem.":[100],"We":[101],"why":[103],"synthesis":[105],"logical":[107,134],"functions":[108,135,181],"threshold":[110],"gates":[111],"or":[112],"is":[115],"active":[117],"research":[118],"area":[119],"in":[120,208],"VLSI":[121],"design":[122],"nanotechnology":[124],"review":[127],"some":[128],"methods":[131],"synthesize":[133,151],"propose":[143],"search":[145],"method":[149],"any":[152,200],"analogical":[156],"inputs":[157],"near":[166,210],"future":[167],"objective.":[168],"Nevertheless":[169],"recognize":[171],"cannot":[178],"approximate":[179],"continuous":[180],"can":[184,197],"easily":[185],"do":[186],"only":[198],"solve":[199],"problem,":[202],"plan":[205],"demonstrate":[207],"future.":[211]},"counts_by_year":[{"year":2015,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}