{"id":"https://openalex.org/W6941343855","doi":"https://doi.org/10.13016/e3ur-eej2","title":"Interpretable Deep Learning for Time Series","display_name":"Interpretable Deep Learning for Time Series","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W6941343855","doi":"https://doi.org/10.13016/e3ur-eej2"},"language":"en","primary_location":{"id":"doi:10.13016/e3ur-eej2","is_oa":true,"landing_page_url":"https://doi.org/10.13016/e3ur-eej2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.13016/e3ur-eej2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ismail, Aya Abdelsalam","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ismail, Aya Abdelsalam","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10451","display_name":"Mycorrhizal Fungi and Plant Interactions","score":0.5705000162124634,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10451","display_name":"Mycorrhizal Fungi and Plant Interactions","score":0.5705000162124634,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.1265999972820282,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10825","display_name":"Plant Pathogens and Fungal Diseases","score":0.03709999844431877,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9793999791145325},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7131999731063843},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5687999725341797},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5676000118255615},{"id":"https://openalex.org/keywords/conflation","display_name":"Conflation","score":0.5669999718666077},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.5396999716758728},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5392000079154968},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5220000147819519}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9793999791145325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7908999919891357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7131999731063843},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6741999983787537},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5687999725341797},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5676000118255615},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5392000079154968},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45559999346733093},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.38109999895095825},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30970001220703125},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.13016/e3ur-eej2","is_oa":true,"landing_page_url":"https://doi.org/10.13016/e3ur-eej2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"doi:10.13016/e3ur-eej2","is_oa":true,"landing_page_url":"https://doi.org/10.13016/e3ur-eej2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Time":[0],"series":[1,94,115,165,265,388],"data":[2,95,353],"emerge":[3],"in":[4,19,38,73,144,158,334,423],"applications":[5,91],"across":[6,138],"many":[7],"critical":[8],"domains,":[9],"including":[10,147],"neuroscience,":[11],"medicine,":[12],"finance,":[13],"economics,":[14],"and":[15,86,89,104,156,169,190,197,203,226,252,273,394],"meteorology.":[16],"However,":[17],"practitioners":[18],"such":[20],"fields":[21],"are":[22,81,96,367],"hesitant":[23],"to":[24,34,53,62,84,92,102,173,201,222,247,310,418],"use":[25],"Deep":[26],"Neural":[27,149],"Networks":[28,150,154],"(DNNs)":[29],"that":[30,194,348],"can":[31,326],"be":[32],"difficult":[33],"interpret.":[35],"For":[36,210],"example,":[37],"clinical":[39],"research,":[40],"one":[41],"might":[42],"ask,":[43],"``Why":[44],"did":[45],"you":[46],"predict":[47],"this":[48,122,259,298],"person":[49],"as":[50,135],"more":[51],"likely":[52],"develop":[54],"Alzheimer's":[55],"disease?\".":[56],"As":[57,316],"a":[58,159,291,303,317,340,410],"result,":[59,318],"research":[60],"efforts":[61],"improve":[63,383],"the":[64,74,106,118,127,176,240,248,283,308,311,322,368,373,384,427,434],"interpretability":[65,109,131,179,266,350],"of":[66,77,108,110,121,129,162,178,218,230,250,258,286,331,345,371,386,429],"deep":[67],"neural":[68,111,140,269,274,279,405,416],"networks":[69,112,417],"have":[70],"significantly":[71],"increased":[72],"last":[75],"couple":[76],"years.":[78],"Nevertheless,":[79],"they":[80],"mainly":[82],"applied":[83],"vision":[85],"language":[87],"tasks,":[88],"their":[90,332],"time":[93,114,145,164,186,224,237,251,264,387,393],"relatively":[97],"unexplored.":[98],"This":[99],"thesis":[100,260],"aims":[101],"identify":[103,205],"address":[105,282],"limitations":[107,285],"for":[113,181,351,415],"data.":[116,166],"In":[117,336],"first":[119],"part":[120,257],"thesis,":[123],"we":[124,289,338],"extensively":[125],"compare":[126],"performance":[128,177],"various":[130],"methods":[132,180,199],"(also":[133],"known":[134],"saliency":[136,198,212,271,379,389,400,411,430],"methods)":[137],"diverse":[139],"architectures":[141,196,244],"commonly":[142],"used":[143,422],"series,":[146],"Recurrent":[148],"(RNNs),":[151],"Temporal":[152],"Convolutional":[153],"(TCNs),":[155],"Transformers":[157],"new":[160,299],"benchmark":[161],"synthetic":[163],"We":[167,192,381,408],"propose":[168],"report":[170],"multiple":[171],"metrics":[172],"empirically":[174],"evaluate":[175],"detecting":[182,232],"feature":[183,206,253,395],"importance":[184,207,396],"over":[185,208,214],"using":[187],"both":[188],"precision":[189],"recall.":[191],"find":[193],"network":[195],"fail":[200,245],"reliably":[202,231],"accurately":[204],"time.":[209,335],"RNNs,":[211],"vanishes":[213],"time,":[215,242],"biasing":[216],"detection":[217],"salient":[219],"features":[220,234,329],"only":[221],"later":[223],"steps,":[225],"are,":[227],"therefore,":[228],"incapable":[229],"important":[233,328],"at":[235,313],"arbitrary":[236],"intervals.":[238],"At":[239],"same":[241],"non-recurrent":[243],"due":[246],"conflation":[249],"domains.":[254],"The":[255],"second":[256],"focuses":[261],"on":[262],"improving":[263],"by":[267,321,365,391],"enhancing":[268],"architectures,":[270],"methods,":[272],"training":[275,406,413],"procedures.":[276],"[a]":[277],"Enhancing":[278,378,404],"architectures:":[280],"To":[281],"architectural":[284],"recurrent":[287],"networks,":[288],"design":[290],"novel":[292],"RNN":[293,325],"cell":[294,300],"structure":[295,301],"(input-cell":[296],"attention);":[297],"preserves":[302],"direct":[304],"gradient":[305],"path":[306],"from":[307],"input":[309],"output":[312],"all":[314],"timesteps.":[315],"explanations":[319,363],"produced":[320,364],"input-cell":[323],"attention":[324],"detect":[327],"regardless":[330],"occurrence":[333],"addition,":[337],"introduce":[339,409],"generalized":[341],"framework,":[342],"Interpretable":[343],"Mixture":[344],"Experts":[346],"(IME),":[347],"provides":[349],"structured":[352],"while":[354,432],"preserving":[355],"accuracy.":[356],"IME":[357,366],"is":[358,375],"an":[359],"inherently-interpretable":[360],"architecture,":[361],"so":[362],"exact":[369],"descriptions":[370],"how":[372],"prediction":[374],"computed.":[376],"[b]":[377],"methods:":[380],"substantially":[382],"quality":[385,428],"maps":[390,431],"detangling":[392],"through":[397],"two-step":[398],"temporal":[399],"rescaling":[401],"(TSR).":[402],"[c]":[403],"procedures:":[407],"guided":[412],"procedure":[414],"reduce":[419],"noisy":[420],"gradients":[421],"predictions,":[424],"which":[425],"improves":[426],"retaining":[433],"model's":[435],"predictive":[436],"performance.":[437]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}