{"id":"https://openalex.org/W2744060663","doi":"https://doi.org/10.1109/isit.2017.8006750","title":"Energy decay and conservation in deep convolutional neural networks","display_name":"Energy decay and conservation in deep convolutional neural networks","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2744060663","doi":"https://doi.org/10.1109/isit.2017.8006750","mag":"2744060663"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2017.8006750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2017.8006750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on Information Theory (ISIT)","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/A5023888160","display_name":"Philipp Grohs","orcid":"https://orcid.org/0000-0001-9205-0969"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Philipp Grohs","raw_affiliation_strings":["Dept. Math., University of Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Dept. Math., University of Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009015123","display_name":"Thomas Wiatowski","orcid":"https://orcid.org/0000-0002-1848-6593"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Thomas Wiatowski","raw_affiliation_strings":["Dept. IT & EE, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dept. IT & EE, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025385120","display_name":"Helmut Bcolcskei","orcid":null},"institutions":[{"id":"https://openalex.org/I2799323385","display_name":"Board of the Swiss Federal Institutes of Technology","ror":"https://ror.org/01rvn4p91","country_code":"CH","type":"government","lineage":["https://openalex.org/I2799323385"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Helmut Bcolcskei","raw_affiliation_strings":["Eidgenossische Technische Hochschule Zurich, Zurich, ZH, CH"],"affiliations":[{"raw_affiliation_string":"Eidgenossische Technische Hochschule Zurich, Zurich, ZH, CH","institution_ids":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023888160"],"corresponding_institution_ids":["https://openalex.org/I129774422"],"apc_list":null,"apc_paid":null,"fwci":0.091,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45716663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1356","last_page":"1360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9997000098228455,"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":0.9997000098228455,"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/T11210","display_name":"Mathematical Analysis and Transform Methods","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2604","display_name":"Applied Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6357313990592957},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6259422302246094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5987191796302795},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5905707478523254},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5901817083358765},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5566643476486206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.55158531665802},{"id":"https://openalex.org/keywords/shearlet","display_name":"Shearlet","score":0.5513392686843872},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4919013977050781},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4624692499637604},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4577215909957886},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43699461221694946},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36199885606765747},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3257308006286621},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13208574056625366},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09512948989868164}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6357313990592957},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6259422302246094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987191796302795},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5905707478523254},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5901817083358765},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5566643476486206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.55158531665802},{"id":"https://openalex.org/C67795661","wikidata":"https://www.wikidata.org/wiki/Q17018993","display_name":"Shearlet","level":3,"score":0.5513392686843872},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4919013977050781},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4624692499637604},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4577215909957886},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43699461221694946},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36199885606765747},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3257308006286621},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13208574056625366},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09512948989868164},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit.2017.8006750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2017.8006750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on Information Theory (ISIT)","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":40,"referenced_works":["https://openalex.org/W97246116","https://openalex.org/W228380312","https://openalex.org/W654435104","https://openalex.org/W1605417594","https://openalex.org/W1762506961","https://openalex.org/W1994906459","https://openalex.org/W1997146646","https://openalex.org/W2021722152","https://openalex.org/W2031621093","https://openalex.org/W2062024414","https://openalex.org/W2066462711","https://openalex.org/W2069912449","https://openalex.org/W2072072671","https://openalex.org/W2093231248","https://openalex.org/W2103835941","https://openalex.org/W2116741198","https://openalex.org/W2119337797","https://openalex.org/W2120731967","https://openalex.org/W2194775991","https://openalex.org/W2208541107","https://openalex.org/W2240077181","https://openalex.org/W2345809749","https://openalex.org/W2406988585","https://openalex.org/W2589910641","https://openalex.org/W2593628332","https://openalex.org/W2605744995","https://openalex.org/W2734655155","https://openalex.org/W2962957157","https://openalex.org/W2963148568","https://openalex.org/W2963803205","https://openalex.org/W3098103643","https://openalex.org/W3158307145","https://openalex.org/W4255272544","https://openalex.org/W4285719527","https://openalex.org/W4290470400","https://openalex.org/W4292024750","https://openalex.org/W4298274615","https://openalex.org/W6686806025","https://openalex.org/W6687483927","https://openalex.org/W6714097516"],"related_works":["https://openalex.org/W2475220750","https://openalex.org/W2016759271","https://openalex.org/W2072476274","https://openalex.org/W2949924583","https://openalex.org/W2018897187","https://openalex.org/W4299617494","https://openalex.org/W1597084776","https://openalex.org/W2571350669","https://openalex.org/W2051098829","https://openalex.org/W166303848"],"abstract_inverted_index":{"Many":[0],"practical":[1],"machine":[2],"learning":[3],"tasks":[4],"employ":[5],"very":[6],"deep":[7,131],"convolutional":[8,132],"neural":[9,133],"networks.":[10],"Such":[11],"large":[12],"depths":[13],"pose":[14],"formidable":[15],"computational":[16],"challenges":[17],"in":[18,46,66,87,99,106,226],"training":[19],"and":[20,135,149,155,172,187],"operating":[21],"the":[22,40,47,52,63,67,81,88,100,103,107,115,159,174,190,205,220,227],"network.":[23,53],"It":[24],"is":[25,76,194],"therefore":[26],"important":[27],"to":[28,36,112,196,210],"understand":[29],"how":[30,61],"many":[31],"layers":[32,208],"are":[33],"actually":[34],"needed":[35,209],"have":[37,211],"most":[38],"of":[39,80,102,114,130,167,185,204,207,219],"input":[41,82,117,221],"signal's":[42,83],"features":[43,84],"be":[44,57,85,197,224],"contained":[45,65,105,225],"feature":[48,68,89,108,138,175,228],"vector":[49,109],"generated":[50],"by":[51,59],"This":[54,119],"question":[55],"can":[56],"formalized":[58],"asking":[60],"quickly":[62],"energy":[64,97,104,124,140,177,223],"maps":[69],"decays":[70,178],"across":[71],"layers.":[72],"In":[73],"addition,":[74],"it":[75],"desirable":[77],"that":[78,113,151],"none":[79],"\u201clost\u201d":[86],"extraction":[90],"network":[91],"or,":[92],"more":[93],"formally,":[94],"we":[95,144],"want":[96],"conservation":[98,125],"sense":[101],"being":[110],"proportional":[111],"corresponding":[116,137],"signal.":[118],"paper":[120],"establishes":[121],"conditions":[122,157],"for":[123,126],"a":[127],"wide":[128],"class":[129],"networks":[134],"characterizes":[136],"map":[139,176],"decay":[141,192],"rates.":[142],"Specifically,":[143],"consider":[145],"general":[146],"scattering":[147],"networks,":[148],"find":[150],"under":[152],"mild":[153],"analyticity":[154],"high-pass":[156],"on":[158],"filters":[160],"(which":[161],"encompass,":[162],"inter":[163],"alia,":[164],"various":[165],"constructions":[166],"Weyl-Heisenberg":[168,188],"filters,":[169,189],"wavelets,":[170],"ridgelets,(\u03b1)-curvelets,":[171],"shearlets)":[173],"at":[179,212],"least":[180,213],"polynomially.":[181],"For":[182],"broad":[183],"families":[184],"wavelets":[186],"guaranteed":[191],"rate":[193],"shown":[195],"exponential.":[198],"Our":[199],"results":[200],"yield":[201],"handy":[202],"estimates":[203],"number":[206],"((1":[214],"\u2212":[215],"\u03b5)":[216],"\u00b7":[217],"100)%":[218],"signal":[222],"vector.":[229]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}