{"id":"https://openalex.org/W3025497567","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207269","title":"On the Information Plane of Autoencoders","display_name":"On the Information Plane of Autoencoders","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3025497567","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207269","mag":"3025497567"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.07783","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nicolas I. Tapia","orcid":null},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":true,"raw_author_name":"Nicolas I. Tapia","raw_affiliation_strings":["Department of Electrical Engineering, Universidad de Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Universidad de Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"last","author":{"id":null,"display_name":"Pablo A. Estevez","orcid":null},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Pablo A. Estevez","raw_affiliation_strings":["Department of Electrical Engineering, Universidad de Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Universidad de Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I69737025"],"apc_list":null,"apc_paid":null,"fwci":1.0971,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82443177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9970999956130981,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9970999956130981,"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/T10320","display_name":"Neural Networks and Applications","score":0.9965000152587891,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9951000213623047,"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/information-bottleneck-method","display_name":"Information bottleneck method","score":0.9401000142097473},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6050999760627747},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5848000049591064},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5805000066757202},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5515000224113464},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4997999966144562},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46869999170303345},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4528999924659729},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information theory","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.9401000142097473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6564000248908997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6166999936103821},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5848000049591064},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5515000224113464},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46230000257492065},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.4406000077724457},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C7797323","wikidata":"https://www.wikidata.org/wiki/Q3798612","display_name":"Pointwise mutual information","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C17825722","wikidata":"https://www.wikidata.org/wiki/Q17285","display_name":"Plane (geometry)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.07783","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07783","pdf_url":"https://arxiv.org/pdf/2005.07783","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":null,"raw_type":"text"},{"id":"pmh:oai:repositorio.uchile.cl:2250/191080","is_oa":true,"landing_page_url":"https://repositorio.uchile.cl/handle/2250/191080","pdf_url":null,"source":{"id":"https://openalex.org/S4306481413","display_name":"Universidad de Chile","issn_l":null,"issn":null,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the International Joint Conference on Neural Networks","raw_type":"Art\u00edculo de revista"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.07783","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.07783","pdf_url":"https://arxiv.org/pdf/2005.07783","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2021792916","https://openalex.org/W2112796928","https://openalex.org/W2593634001","https://openalex.org/W2880214242","https://openalex.org/W2962783375","https://openalex.org/W2963386266","https://openalex.org/W2964184826","https://openalex.org/W2977118166","https://openalex.org/W6638667902","https://openalex.org/W6678323213","https://openalex.org/W6748205129","https://openalex.org/W6752051073","https://openalex.org/W6757512965"],"related_works":[],"abstract_inverted_index":{"The":[0,35,88],"training":[1],"dynamics":[2],"of":[3,31,67,86],"hidden":[4],"layers":[5,42],"in":[6,12,54,112,128,176],"deep":[7],"learning":[8,73,197],"are":[9],"poorly":[10],"understood":[11],"theory.":[13,157],"Recently,":[14],"the":[15,28,52,65,68,71,84,113,117,129,156,191,195],"Information":[16,36],"Plane":[17],"(IP)":[18],"was":[19],"proposed":[20,127,148],"to":[21,51,136,155,169,173],"analyze":[22],"them,":[23],"which":[24],"is":[25,60],"based":[26,123],"on":[27,194],"information-theoretic":[29],"concept":[30],"mutual":[32],"information":[33,45],"(MI).":[34],"Bottleneck":[37],"(IB)":[38],"theory":[39,89],"predicts":[40,90],"that":[41,91,140],"maximize":[43],"relevant":[44],"and":[46,143,187],"compress":[47,102],"irrelevant":[48],"information.":[49],"Due":[50],"limitations":[53,183],"MI":[55,124,175],"estimation":[56],"from":[57],"samples,":[58],"there":[59],"an":[61],"ongoing":[62,192],"debate":[63,193],"about":[64],"properties":[66],"IP":[69,85,160],"for":[70,83,161],"supervised":[72,196],"case.":[74,198],"In":[75,179],"this":[76,180],"work,":[77],"we":[78,119,150],"derive":[79],"a":[80,95,106,121,133,167],"theoretical":[81,159],"convergence":[82],"autoencoders.":[87],"ideal":[92],"autoencoders":[93,162],"with":[94,190],"large":[96],"bottleneck":[97],"layer":[98],"size":[99,108],"do":[100],"not":[101],"input":[103],"information,":[104],"whereas":[105],"small":[107],"causes":[109],"compression":[110],"only":[111],"encoder":[114],"layers.":[115],"For":[116],"experiments,":[118],"use":[120],"Gram-matrix":[122],"estimator":[125],"recently":[126],"literature.":[130],"We":[131],"propose":[132],"new":[134,171],"rule":[135],"adjust":[137],"its":[138],"parameters":[139],"compensates":[141],"scale":[142],"dimensionality":[144],"effects.":[145],"Using":[146],"our":[147],"rule,":[149],"obtain":[151],"experimental":[152,182],"IPs":[153],"closer":[154],"Our":[158],"could":[163,184],"be":[164,185],"used":[165],"as":[166],"benchmark":[168],"validate":[170],"methods":[172],"estimate":[174],"neural":[177],"networks.":[178],"way,":[181],"recognized":[186],"corrected,":[188],"helping":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-05-21T00:00:00"}