{"id":"https://openalex.org/W3045150439","doi":"https://doi.org/10.1109/tnnls.2020.3005348","title":"Deep Residual Autoencoders for Expectation Maximization-Inspired Dictionary Learning","display_name":"Deep Residual Autoencoders for Expectation Maximization-Inspired Dictionary Learning","publication_year":2020,"publication_date":"2020-07-20","ids":{"openalex":"https://openalex.org/W3045150439","doi":"https://doi.org/10.1109/tnnls.2020.3005348","mag":"3045150439","pmid":"https://pubmed.ncbi.nlm.nih.gov/32687471"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.3005348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3005348","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.08827","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088730122","display_name":"Bahareh Tolooshams","orcid":"https://orcid.org/0000-0002-5955-6535"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahareh Tolooshams","raw_affiliation_strings":["School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5955-6535","affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sourav Dey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sourav Dey","raw_affiliation_strings":["Manifold AI, Oakland, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Manifold AI, Oakland, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002643771","display_name":"Demba Ba","orcid":"https://orcid.org/0000-0002-1139-1030"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Demba Ba","raw_affiliation_strings":["School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1139-1030","affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9654,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.95336196,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":"6","first_page":"2415","last_page":"2429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9984999895095825,"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":0.7364712953567505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6085252165794373},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5099653005599976},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5081593990325928},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.46514689922332764},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4484074115753174},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.42257586121559143},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.4193258583545685},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4096005856990814},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3959420323371887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7364712953567505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6085252165794373},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5099653005599976},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5081593990325928},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.46514689922332764},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4484074115753174},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.42257586121559143},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.4193258583545685},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4096005856990814},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3959420323371887}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2020.3005348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3005348","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:32687471","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32687471","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},{"id":"pmh:oai:arXiv.org:1904.08827","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.08827","pdf_url":"https://arxiv.org/pdf/1904.08827","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.08827","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.08827","pdf_url":"https://arxiv.org/pdf/1904.08827","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5910680597","display_name":null,"funder_award_id":"DMS-1764269","funder_id":"https://openalex.org/F4320309622","funder_display_name":"Harvard University"},{"id":"https://openalex.org/G8023359762","display_name":null,"funder_award_id":"W911NF-16-1-0368","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320309622","display_name":"Harvard University","ror":"https://ror.org/03vek6s52"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1580389772","https://openalex.org/W1831449718","https://openalex.org/W1959608418","https://openalex.org/W1981562201","https://openalex.org/W1982652137","https://openalex.org/W1986931325","https://openalex.org/W1989775522","https://openalex.org/W1996550590","https://openalex.org/W2015418199","https://openalex.org/W2029507661","https://openalex.org/W2049633694","https://openalex.org/W2078204800","https://openalex.org/W2100556411","https://openalex.org/W2102380305","https://openalex.org/W2114747787","https://openalex.org/W2115429828","https://openalex.org/W2115706991","https://openalex.org/W2117259536","https://openalex.org/W2117289172","https://openalex.org/W2118103795","https://openalex.org/W2132984323","https://openalex.org/W2135046866","https://openalex.org/W2154332973","https://openalex.org/W2156387975","https://openalex.org/W2160547390","https://openalex.org/W2163605009","https://openalex.org/W2164278908","https://openalex.org/W2164452299","https://openalex.org/W2171406132","https://openalex.org/W2186094539","https://openalex.org/W2194775991","https://openalex.org/W2293078015","https://openalex.org/W2618530766","https://openalex.org/W2749560167","https://openalex.org/W2760027020","https://openalex.org/W2766452532","https://openalex.org/W2785523195","https://openalex.org/W2805841154","https://openalex.org/W2914484425","https://openalex.org/W2952071070","https://openalex.org/W2953046278","https://openalex.org/W2962709635","https://openalex.org/W2963197835","https://openalex.org/W2963322354","https://openalex.org/W2963372528","https://openalex.org/W2963623200","https://openalex.org/W2963697946","https://openalex.org/W2964054038","https://openalex.org/W2964121744","https://openalex.org/W2971076774","https://openalex.org/W2972890883","https://openalex.org/W4238404964","https://openalex.org/W4239719188","https://openalex.org/W4248646870","https://openalex.org/W4250297470","https://openalex.org/W4292363360","https://openalex.org/W4293456497","https://openalex.org/W4297801963","https://openalex.org/W4322615131","https://openalex.org/W6628781318","https://openalex.org/W6631190155","https://openalex.org/W6638670064","https://openalex.org/W6638896900","https://openalex.org/W6640963894","https://openalex.org/W6677645113","https://openalex.org/W6682889407","https://openalex.org/W6724411756","https://openalex.org/W6730998768","https://openalex.org/W6752111200","https://openalex.org/W6767423860"],"related_works":["https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W4392946183","https://openalex.org/W3088732000","https://openalex.org/W2115605526","https://openalex.org/W3093883775","https://openalex.org/W1539246760","https://openalex.org/W2786746258","https://openalex.org/W4225893763","https://openalex.org/W2788727425"],"abstract_inverted_index":{"We":[0,173],"introduce":[1],"a":[2,20,78,97,103,119,127,135,156,164],"neural-network":[3],"architecture,":[4],"termed":[5],"the":[6,31,34,50,54,65,68,72,75,132,140,151,160,167,186,195,207,220],"constrained":[7],"recurrent":[8,98],"sparse":[9,79],"autoencoder":[10],"(CRsAE),":[11],"that":[12,48,162,179,185,211],"solves":[13],"convolutional":[14],"dictionary":[15,23,38,55,141,145],"learning":[16,24,39,190],"problems,":[17],"thus":[18],"establishing":[19],"link":[21],"between":[22],"and":[25,56,134,184,217],"neural":[26,99],"networks.":[27],"Specifically,":[28],"we":[29,209],"leverage":[30],"interpretation":[32],"of":[33,53,64,71,203,222],"alternating-minimization":[35],"algorithm":[36,44,87],"for":[37,189],"as":[40,74,96,102],"an":[41,83,176,199],"approximate":[42],"expectation-maximization":[43],"to":[45,77,131,159,194,201],"develop":[46],"autoencoders":[47],"enable":[49],"simultaneous":[51],"training":[52],"regularization":[57,152],"parameter":[58,153,168],"(ReLU":[59],"bias).":[60],"The":[61,90,114,122,147],"forward":[62],"pass":[63],"encoder":[66,91,133,161],"approximates":[67],"sufficient":[69],"statistics":[70],"E-step":[73],"solution":[76],"coding":[80],"problem,":[81],"using":[82],"iterative":[84],"proximal":[85],"gradient":[86],"called":[88],"FISTA.":[89],"can":[92],"be":[93],"interpreted":[94],"either":[95],"network":[100],"or":[101],"deep":[104],"residual":[105],"network,":[106],"with":[107,229],"two-sided":[108],"ReLU":[109],"nonlinearities":[110],"in":[111,144,175],"both":[112],"cases.":[113],"M-step":[115],"is":[116,192],"implemented":[117],"via":[118],"two-stage":[120],"backpropagation.":[121],"first":[123],"stage":[124,149],"relies":[125],"on":[126,166,232],"linear":[128],"decoder":[129],"applied":[130],"norm-squared":[136],"loss.":[137],"It":[138],"parallels":[139],"update":[142],"step":[143],"learning.":[146],"second":[148],"updates":[150],"by":[154,170,226],"applying":[155],"loss":[157],"function":[158],"includes":[163],"prior":[165],"motivated":[169],"Bayesian":[171],"statistics.":[172],"demonstrate":[174,210],"image-denoising":[177],"task":[178],"CRsAE":[180,212],"learns":[181,213],"Gabor-like":[182],"filters":[183],"EM-inspired":[187],"approach":[188],"biases":[191],"superior":[193],"conventional":[196],"approach.":[197],"In":[198],"application":[200],"recordings":[202],"electrical":[204],"activity":[205],"from":[206],"brain,":[208],"realistic":[214],"spike":[215,224],"templates":[216],"speeds":[218],"up":[219],"process":[221],"identifying":[223],"times":[225],"900\u00d7":[227],"compared":[228],"algorithms":[230],"based":[231],"convex":[233],"optimization.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}