{"id":"https://openalex.org/W2740247811","doi":"https://doi.org/10.1109/cwit.2017.7994828","title":"Optimality of inference in hierarchical coding for distributed object-based representations","display_name":"Optimality of inference in hierarchical coding for distributed object-based representations","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2740247811","doi":"https://doi.org/10.1109/cwit.2017.7994828","mag":"2740247811"},"language":"en","primary_location":{"id":"doi:10.1109/cwit.2017.7994828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cwit.2017.7994828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 15th Canadian Workshop on Information Theory (CWIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5088988384","display_name":"Simon Brodeur","orcid":null},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Simon Brodeur","raw_affiliation_strings":["NECOTIS, Departement genie electrique et genie informatique, Universite de Sherbrooke, Sherbrooke, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NECOTIS, Departement genie electrique et genie informatique, Universite de Sherbrooke, Sherbrooke, Canada","institution_ids":["https://openalex.org/I135117807"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026332327","display_name":"Jean Rouat","orcid":"https://orcid.org/0000-0002-9306-426X"},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jean Rouat","raw_affiliation_strings":["NECOTIS, Departement genie electrique et genie informatique, Universite de Sherbrooke, Sherbrooke, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NECOTIS, Departement genie electrique et genie informatique, Universite de Sherbrooke, Sherbrooke, Canada","institution_ids":["https://openalex.org/I135117807"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135117807"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09991091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10057","display_name":"Face and Expression Recognition","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.6818666458129883},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5769386291503906},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.561724841594696},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5417919158935547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4286542534828186},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3597104847431183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818666458129883},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5769386291503906},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.561724841594696},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5417919158935547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4286542534828186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3597104847431183},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cwit.2017.7994828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cwit.2017.7994828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 15th Canadian Workshop on Information Theory (CWIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334841","display_name":"Fonds de recherche du Qu\u00e9bec \u2013 Nature et technologies","ror":"https://ror.org/00b9f9778"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W114250020","https://openalex.org/W1700083040","https://openalex.org/W2020719522","https://openalex.org/W2028781966","https://openalex.org/W2042554576","https://openalex.org/W2102098892","https://openalex.org/W2104371740","https://openalex.org/W2107745473","https://openalex.org/W2117289172","https://openalex.org/W2128859735","https://openalex.org/W2130542426","https://openalex.org/W2163398148","https://openalex.org/W2163922914","https://openalex.org/W2336763592","https://openalex.org/W4239515185","https://openalex.org/W6677409489"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Hierarchical":[0],"approaches":[1,22],"for":[2,56,83,142,158,164],"representation":[3,35,59],"learning":[4,70],"have":[5,147],"the":[6,25,29,49,66,102,114,128,134,139,150,174,190],"ability":[7],"to":[8,100,126,154,195],"encode":[9,101],"relevant":[10],"features":[11],"at":[12],"multiple":[13,50],"scales":[14],"or":[15,31],"levels":[16,51,112],"of":[17,41,52,60,68,113,121,176],"abstraction.":[18],"However,":[19,161],"most":[20],"hierarchical":[21,84],"exploit":[23],"only":[24],"last":[26],"level":[27],"in":[28,62,182,203],"hierarchy,":[30],"provide":[32],"a":[33,38,72,78,91],"multiscale":[34],"that":[36,45,149,180],"holds":[37],"significant":[39],"amount":[40],"redundancy.":[42],"We":[43,172],"argue":[44],"removing":[46],"redundancy":[47],"across":[48,111],"abstraction":[53],"is":[54,152],"important":[55],"an":[57],"efficient":[58],"compositionality":[61],"object-based":[63,209],"representations.":[64,210],"With":[65],"perspective":[67],"feature":[69],"as":[71],"data":[73],"compression":[74],"operation,":[75],"we":[76],"propose":[77],"new":[79,187],"greedy":[80],"inference":[81],"algorithm":[82,151],"sparse":[85],"coding.":[86],"Convolutional":[87],"matching":[88,178],"pursuit":[89,179],"with":[90,133,167],"L":[92,197],"<sup":[93,198],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[94,199],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</sup>":[95,200],"-norm":[96,201],"constraint":[97,202],"was":[98],"used":[99],"input":[103],"signal":[104],"into":[105],"compact":[106,206],"and":[107,117,131,207],"non-redundant":[108],"codes":[109,157],"distributed":[110,208],"hierarchy.":[115],"Simple":[116],"complex":[118,165],"synthetic":[119],"datasets":[120],"temporal":[122],"signals":[123,166],"were":[124],"created":[125],"evaluate":[127],"encoding":[129],"efficiency":[130],"compare":[132],"theoretical":[135],"lower":[136],"bounds":[137],"on":[138],"information":[140],"rate":[141],"those":[143],"signals.":[144,160],"Empirical":[145],"evidence":[146],"shown":[148],"able":[153],"infer":[155],"near-optimal":[156],"simple":[159],"it":[162],"failed":[163],"strong":[168],"overlapping":[169],"between":[170],"objects.":[171],"explain":[173],"inefficiency":[175],"convolutional":[177],"occurred":[181],"such":[183],"case.":[184],"This":[185],"brings":[186],"insights":[188],"about":[189],"NP-hard":[191],"optimization":[192],"problem":[193],"related":[194],"using":[196],"inferring":[204],"optimally":[205]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}