{"id":"https://openalex.org/W3090939700","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206800","title":"Interpretability vs. Complexity: The Friction in Deep Neural Networks","display_name":"Interpretability vs. Complexity: The Friction in Deep Neural Networks","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090939700","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206800","mag":"3090939700"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206800","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":["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/A5019780158","display_name":"Jos\u00e9 Pereira Amorim","orcid":"https://orcid.org/0000-0002-9477-0078"},"institutions":[{"id":"https://openalex.org/I4210111164","display_name":"IPO Porto","ror":"https://ror.org/027ras364","country_code":"PT","type":"healthcare","lineage":["https://openalex.org/I4210111164"]},{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Jose P. Amorim","raw_affiliation_strings":["IPO-Porto Research Centre and CISUC, University of Coimbra, Portugal"],"affiliations":[{"raw_affiliation_string":"IPO-Porto Research Centre and CISUC, University of Coimbra, Portugal","institution_ids":["https://openalex.org/I76903346","https://openalex.org/I4210111164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065859612","display_name":"Pedro Henriques Abreu","orcid":"https://orcid.org/0000-0002-9278-8194"},"institutions":[{"id":"https://openalex.org/I76903346","display_name":"University of Coimbra","ror":"https://ror.org/04z8k9a98","country_code":"PT","type":"education","lineage":["https://openalex.org/I76903346"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pedro H. Abreu","raw_affiliation_strings":["CISUC, University of Coimbra, Portugal"],"affiliations":[{"raw_affiliation_string":"CISUC, University of Coimbra, Portugal","institution_ids":["https://openalex.org/I76903346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060822066","display_name":"Mauricio Reyes","orcid":"https://orcid.org/0000-0002-2434-9990"},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mauricio Reyes","raw_affiliation_strings":["Medical Image Analysis, University of Bern, Switzerland"],"affiliations":[{"raw_affiliation_string":"Medical Image Analysis, University of Bern, Switzerland","institution_ids":["https://openalex.org/I118564535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082299802","display_name":"Jo\u00e3o Santos","orcid":"https://orcid.org/0000-0003-2465-5143"},"institutions":[{"id":"https://openalex.org/I4210111164","display_name":"IPO Porto","ror":"https://ror.org/027ras364","country_code":"PT","type":"healthcare","lineage":["https://openalex.org/I4210111164"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joao Santos","raw_affiliation_strings":["IPO-Porto Research Centre, Porto, Portugal"],"affiliations":[{"raw_affiliation_string":"IPO-Porto Research Centre, Porto, Portugal","institution_ids":["https://openalex.org/I4210111164"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019780158"],"corresponding_institution_ids":["https://openalex.org/I4210111164","https://openalex.org/I76903346"],"apc_list":null,"apc_paid":null,"fwci":1.193,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83755715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9997000098228455,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9997000098228455,"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":0.9927999973297119,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9842000007629395,"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/interpretability","display_name":"Interpretability","score":0.9439880847930908},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7471400499343872},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7261243462562561},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.7204279899597168},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6871089935302734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6707214117050171},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6368064880371094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5929791927337646},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5797656774520874},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.43267592787742615},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43231475353240967},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4154098927974701},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.398442804813385}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9439880847930908},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7471400499343872},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7261243462562561},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.7204279899597168},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6871089935302734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6707214117050171},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6368064880371094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5929791927337646},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5797656774520874},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.43267592787742615},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43231475353240967},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4154098927974701},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.398442804813385},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206800","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W1849277567","https://openalex.org/W2123045220","https://openalex.org/W2163605009","https://openalex.org/W2195388612","https://openalex.org/W2282821441","https://openalex.org/W2439568532","https://openalex.org/W2551974706","https://openalex.org/W2604272474","https://openalex.org/W2964045325","https://openalex.org/W3118608800","https://openalex.org/W4289699961","https://openalex.org/W4299408792","https://openalex.org/W6639204139","https://openalex.org/W6677995690","https://openalex.org/W6718991148","https://openalex.org/W6730035438","https://openalex.org/W6753724168","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W4319993887","https://openalex.org/W4297789176","https://openalex.org/W2768346313","https://openalex.org/W2963249138","https://openalex.org/W2998594699","https://openalex.org/W2294590153","https://openalex.org/W4220659530"],"abstract_inverted_index":{"Saliency":[0],"maps":[1,55,72,156],"have":[2],"been":[3],"used":[4],"as":[5],"one":[6],"possibility":[7],"to":[8,33,41,77,104,146],"interpret":[9],"deep":[10],"neural":[11],"networks.":[12],"This":[13],"method":[14],"estimates":[15],"the":[16,22,44,47,50,53,67,70,78,83,89,92,108,121,139,147],"relevance":[17],"of":[18,37,46,52,82,91,94,114,134],"each":[19],"pixel":[20],"in":[21,56,66,88],"image":[23],"classification,":[24],"with":[25,128,157],"higher":[26,148],"values":[27],"representing":[28],"pixels":[29],"which":[30],"contribute":[31],"positively":[32],"classification.":[34],"The":[35],"goal":[36],"this":[38],"study":[39],"is":[40],"understand":[42],"how":[43,64],"complexity":[45],"network":[48],"affects":[49,69],"interpretabilty":[51],"saliency":[54,71,96,155],"classification":[57,80],"tasks.":[58],"To":[59],"achieve":[60],"that,":[61],"we":[62],"investigate":[63],"changes":[65],"regularization":[68,130,143],"produced,":[73],"and":[74],"their":[75],"fidelity":[76,93],"overall":[79],"process":[81],"network.The":[84],"experimental":[85],"setup":[86],"consists":[87],"calculation":[90],"five":[95],"map":[97],"methods":[98],"that":[99,126],"were":[100],"compare,":[101],"applying":[102],"them":[103],"models":[105,127],"trained":[106],"on":[107,117],"CIFAR-10":[109],"dataset,":[110],"using":[111],"different":[112],"levels":[113],"weight":[115],"decay":[116],"some":[118],"or":[119,151],"all":[120],"layers.":[122],"Achieved":[123],"results":[124],"show":[125],"lower":[129],"are":[131],"statistically":[132],"(significance":[133],"5%)":[135],"more":[136,158],"interpretable":[137],"than":[138],"other":[140],"models.":[141],"Also,":[142],"applied":[144],"only":[145],"convolutional":[149],"layers":[150,153],"fully-connected":[152],"produce":[154],"fidelity.":[159]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}