{"id":"https://openalex.org/W3045825034","doi":"https://doi.org/10.1109/tnnls.2020.3007259","title":"Enhancing Explainability of Neural Networks Through Architecture Constraints","display_name":"Enhancing Explainability of Neural Networks Through Architecture Constraints","publication_year":2020,"publication_date":"2020-07-27","ids":{"openalex":"https://openalex.org/W3045825034","doi":"https://doi.org/10.1109/tnnls.2020.3007259","mag":"3045825034","pmid":"https://pubmed.ncbi.nlm.nih.gov/32716891"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.3007259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3007259","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5065081397","display_name":"Zebin Yang","orcid":"https://orcid.org/0000-0001-5683-7502"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zebin Yang","raw_affiliation_strings":["Department of Statistics and Actuarial Science, The University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Actuarial Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664060","display_name":"Aijun Zhang","orcid":"https://orcid.org/0000-0001-9729-9018"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Aijun Zhang","raw_affiliation_strings":["Department of Statistics and Actuarial Science, The University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9729-9018","affiliations":[{"raw_affiliation_string":"Department of Statistics and Actuarial Science, The University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001331464","display_name":"Agus Sudjianto","orcid":"https://orcid.org/0000-0003-0846-9746"},"institutions":[{"id":"https://openalex.org/I166794780","display_name":"Wells Fargo (United States)","ror":"https://ror.org/037r2ff59","country_code":"US","type":"company","lineage":["https://openalex.org/I166794780"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Agus Sudjianto","raw_affiliation_strings":["Corporate Model Risk at Wells Fargo, Charlotte, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Corporate Model Risk at Wells Fargo, Charlotte, NC, USA","institution_ids":["https://openalex.org/I166794780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.1263,"has_fulltext":false,"cited_by_count":104,"citation_normalized_percentile":{"value":0.98346465,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"32","issue":"6","first_page":"2610","last_page":"2621"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9998000264167786,"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/T12676","display_name":"Machine Learning and ELM","score":0.9998000264167786,"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":0.9991999864578247,"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":0.9983000159263611,"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":0.917802095413208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.665155291557312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6619794368743896},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.5659245848655701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5379951596260071},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5265317559242249},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4773407280445099},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.4664342701435089},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4638429284095764},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36714664101600647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19280725717544556}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.917802095413208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.665155291557312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6619794368743896},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.5659245848655701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5379951596260071},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5265317559242249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4773407280445099},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.4664342701435089},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4638429284095764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36714664101600647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19280725717544556},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2020.3007259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3007259","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:32716891","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32716891","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322170","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1554944419","https://openalex.org/W1678356000","https://openalex.org/W1821462560","https://openalex.org/W1848802304","https://openalex.org/W1975900269","https://openalex.org/W1988115241","https://openalex.org/W2019176983","https://openalex.org/W2030818161","https://openalex.org/W2086953401","https://openalex.org/W2091886411","https://openalex.org/W2095701484","https://openalex.org/W2111072639","https://openalex.org/W2114354594","https://openalex.org/W2125847307","https://openalex.org/W2134797427","https://openalex.org/W2136175429","https://openalex.org/W2138459548","https://openalex.org/W2146766088","https://openalex.org/W2171033594","https://openalex.org/W2282821441","https://openalex.org/W2294370754","https://openalex.org/W2564414379","https://openalex.org/W2593996946","https://openalex.org/W2740586183","https://openalex.org/W2758000438","https://openalex.org/W2797583072","https://openalex.org/W2806087506","https://openalex.org/W2806874342","https://openalex.org/W2888410376","https://openalex.org/W2954503794","https://openalex.org/W2964121744","https://openalex.org/W2993421702","https://openalex.org/W3035517615","https://openalex.org/W4249303080","https://openalex.org/W4298876635","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6638523607","https://openalex.org/W6679909955","https://openalex.org/W6730804571","https://openalex.org/W6751804815","https://openalex.org/W6752336104","https://openalex.org/W6754270545"],"related_works":["https://openalex.org/W3196180327","https://openalex.org/W2115605526","https://openalex.org/W3093883775","https://openalex.org/W1539246760","https://openalex.org/W2786746258","https://openalex.org/W4225893763","https://openalex.org/W2788727425","https://openalex.org/W2405196115","https://openalex.org/W2104893957","https://openalex.org/W2971074373"],"abstract_inverted_index":{"Prediction":[0],"accuracy":[1,177],"and":[2,64,85,120,148,159],"model":[3,35,86,169],"explainability":[4,45],"are":[5,22,101],"the":[6,44,50,94,113,118,121,126,138,166,171],"two":[7],"most":[8],"important":[9],"objectives":[10],"when":[11],"developing":[12],"machine":[13],"learning":[14,157],"algorithms":[15],"to":[16,24,42,71,141],"solve":[17],"real-world":[18],"problems.":[19],"Neural":[20],"networks":[21,48],"known":[23],"possess":[25],"good":[26],"prediction":[27,83,176],"performance":[28,84],"but":[29],"suffer":[30],"from":[31],"a":[32,79,105,183,190],"lack":[33],"of":[34,46,173],"interpretability.":[36,87,181],"In":[37],"this":[38],"article,":[39],"we":[40,136],"propose":[41],"enhance":[43],"neural":[47,75],"through":[49],"following":[51],"architecture":[52],"constraints:":[53],"1)":[54],"sparse":[55],"additive":[56],"subnetworks;":[57],"2)":[58],"projection":[59,127],"pursuit":[60],"with":[61,78],"orthogonality":[62],"constraint;":[63],"3)":[65],"smooth":[66],"function":[67],"approximation.":[68],"It":[69,162],"leads":[70],"an":[72],"enhanced":[73],"explainable":[74],"network":[76],"(ExNN)":[77],"superior":[80],"balance":[81],"between":[82],"We":[88],"derive":[89],"sufficient":[90],"identifiability":[91],"conditions":[92],"for":[93,116,124],"proposed":[95,139,167],"ExNN":[96,168],"model.":[97],"The":[98],"multiple":[99],"parameters":[100],"simultaneously":[102],"estimated":[103],"by":[104],"modified":[106],"minibatch":[107],"gradient":[108],"descent":[109],"method":[110,140],"based":[111],"on":[112],"backpropagation":[114],"algorithm":[115],"calculating":[117],"derivatives":[119],"Cayley":[122],"transform":[123],"preserving":[125],"orthogonality.":[128],"Through":[129],"simulation":[130],"study":[131],"under":[132],"six":[133],"different":[134],"scenarios,":[135],"compare":[137],"several":[142],"benchmarks,":[143],"including":[144],"least":[145],"absolute":[146],"shrinkage":[147],"selection":[149],"operator,":[150],"support":[151],"vector":[152],"machine,":[153,158],"random":[154],"forest,":[155],"extreme":[156],"multilayer":[160],"perceptron.":[161],"is":[163,187],"shown":[164],"that":[165],"keeps":[170],"flexibility":[172],"pursuing":[174],"high":[175],"while":[178],"attaining":[179],"improved":[180],"Finally,":[182],"real":[184],"data":[185],"example":[186],"employed":[188],"as":[189],"showcase":[191],"application.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}