{"id":"https://openalex.org/W4226050524","doi":"https://doi.org/10.1109/lsp.2022.3160372","title":"Positive Sparse Signal Denoising: What Does a CNN Learn?","display_name":"Positive Sparse Signal Denoising: What Does a CNN Learn?","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4226050524","doi":"https://doi.org/10.1109/lsp.2022.3160372"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3160372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3160372","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-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/A5033676037","display_name":"Abdullah Al-Shabili","orcid":"https://orcid.org/0000-0003-4616-4134"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abdullah H. Al-Shabili","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New York University Tandon School of Engineering, Brooklyn, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University Tandon School of Engineering, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058321875","display_name":"Ivan Selesnick","orcid":"https://orcid.org/0000-0002-4939-3971"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Selesnick","raw_affiliation_strings":["Department of Electrical and Computer Engineering, New York University Tandon School of Engineering, Brooklyn, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, New York University Tandon School of Engineering, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033676037"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":1.2077,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79625733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"912","last_page":"916"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9997000098228455,"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/T10320","display_name":"Neural Networks and Applications","score":0.9976999759674072,"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":0.7929304838180542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6765228509902954},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6713395118713379},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6500881314277649},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.6037488579750061},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6036034822463989},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.6017718315124512},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.554835855960846},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4704149067401886},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4123998284339905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35731562972068787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24394503235816956},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12261694669723511},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09509885311126709}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7929304838180542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6765228509902954},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6713395118713379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6500881314277649},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6037488579750061},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6036034822463989},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.6017718315124512},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.554835855960846},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4704149067401886},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4123998284339905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35731562972068787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24394503235816956},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12261694669723511},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09509885311126709},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2022.3160372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3160372","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1946620893","https://openalex.org/W1965125844","https://openalex.org/W2074682976","https://openalex.org/W2087416986","https://openalex.org/W2140742952","https://openalex.org/W2163761533","https://openalex.org/W2220485312","https://openalex.org/W2558748708","https://openalex.org/W2573726823","https://openalex.org/W2762685704","https://openalex.org/W2765431787","https://openalex.org/W2782977076","https://openalex.org/W2785985567","https://openalex.org/W2810470036","https://openalex.org/W2911290743","https://openalex.org/W2919115771","https://openalex.org/W2963074136","https://openalex.org/W2963814976","https://openalex.org/W3006592723","https://openalex.org/W3021094251","https://openalex.org/W3024822880","https://openalex.org/W3047002475","https://openalex.org/W3098306969","https://openalex.org/W3098900881","https://openalex.org/W3099883911","https://openalex.org/W3100774664","https://openalex.org/W3101311698","https://openalex.org/W3106769307","https://openalex.org/W3112297092","https://openalex.org/W3133902371","https://openalex.org/W4288349471","https://openalex.org/W6631190155","https://openalex.org/W6679698722","https://openalex.org/W6684111346","https://openalex.org/W6729999211","https://openalex.org/W6751347407","https://openalex.org/W6762438721","https://openalex.org/W6762904343","https://openalex.org/W6764313512","https://openalex.org/W6788030356"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2133587243"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"provide":[4],"impressive":[5],"empirical":[6,66],"success":[7],"in":[8,88],"various":[9],"tasks;":[10],"however,":[11],"their":[12],"inner":[13],"workings":[14],"generally":[15],"lack":[16],"interpretability.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21,26,79],"interpret":[22],"shallow":[23],"CNNs":[24],"that":[25,49],"have":[27],"trained":[28,45],"for":[29],"the":[30,44,50,69],"task":[31],"of":[32,68,102,111],"positive":[33],"sparse":[34],"signal":[35],"denoising.":[36],"We":[37,47],"identify":[38],"and":[39,84,108],"analyze":[40],"common":[41],"structures":[42],"among":[43],"CNNs.":[46],"show":[48],"learned":[51],"CNN":[52,82,97],"denoisers":[53,83],"can":[54],"be":[55],"interpreted":[56,96],"as":[57],"a":[58,103,109],"nonlinear":[59],"locally-adaptive":[60],"thresholding":[61,114],"procedure,":[62],"which":[63],"is":[64,99],"an":[65,100],"approximation":[67],"minimum":[70],"mean":[71],"square":[72],"error":[73],"estimator.":[74],"Based":[75],"on":[76],"our":[77],"interpretation,":[78],"train":[80],"constrained":[81],"demonstrate":[85],"no":[86],"loss":[87],"performance":[89],"despite":[90],"having":[91],"fewer":[92],"trainable":[93],"parameters.":[94],"The":[95],"denoiser":[98],"instance":[101],"multivariate":[104],"spline":[105],"regression":[106],"model,":[107],"generalization":[110],"classical":[112],"proximal":[113],"operators.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}