{"id":"https://openalex.org/W3172492166","doi":null,"title":"Householder-Absolute Neural Layers For High Variability and Deep Trainability.","display_name":"Householder-Absolute Neural Layers For High Variability and Deep Trainability.","publication_year":2021,"publication_date":"2021-06-08","ids":{"openalex":"https://openalex.org/W3172492166","mag":"3172492166"},"language":"en","primary_location":{"id":"mag:3172492166","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.04088.pdf","pdf_url":null,"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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.04088.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053245253","display_name":"Yueyao Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yueyao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343712","display_name":"Yin Zhang\u22c6","orcid":"https://orcid.org/0000-0002-1772-0763","observed_orcids":["https://orcid.org/0000-0002-1772-0763"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin Zhang\u22c6","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1772-0763","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9878000020980835,"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/T10320","display_name":"Neural Networks and Applications","score":0.9878000020980835,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.004900000058114529,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.003800000064074993,"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/vanishing-and-exploding-gradients","display_name":"vanishing and exploding gradients","score":0.8379999995231628},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.6399999856948853}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7637616395950317},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7362880110740662},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.735863208770752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5502778887748718},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5052950978279114},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.481706440448761},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.45087313652038574},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4373228847980499},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4285426139831543},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42848771810531616},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4284587502479553},{"id":"https://openalex.org/C124978682","wikidata":"https://www.wikidata.org/wiki/Q1201019","display_name":"Proof of concept","level":2,"score":0.41789355874061584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40685760974884033},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3127802610397339},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.12607085704803467},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1237422525882721},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.07598590850830078},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3172492166","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.04088.pdf","pdf_url":null,"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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3172492166","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.04088.pdf","pdf_url":null,"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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1677182931","https://openalex.org/W1800356822","https://openalex.org/W2023320048","https://openalex.org/W2097694726","https://openalex.org/W2116479686","https://openalex.org/W2163605009","https://openalex.org/W2559626456","https://openalex.org/W2587753047","https://openalex.org/W2759764766","https://openalex.org/W2786598939","https://openalex.org/W2786968074","https://openalex.org/W2789210533","https://openalex.org/W2808460953","https://openalex.org/W2890966191","https://openalex.org/W2963992014","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W2996609754","https://openalex.org/W3034222740","https://openalex.org/W3040743533","https://openalex.org/W3118608800","https://openalex.org/W3141259390","https://openalex.org/W3161782310"],"related_works":["https://openalex.org/W4379510966","https://openalex.org/W4393181368","https://openalex.org/W2989908956","https://openalex.org/W4366999905","https://openalex.org/W7142420361","https://openalex.org/W3161782310","https://openalex.org/W4407949132","https://openalex.org/W3159847323","https://openalex.org/W4416131835","https://openalex.org/W7133762212"],"abstract_inverted_index":{"We":[0,82],"propose":[1],"a":[2,72,143,151,161],"new":[3],"architecture":[4],"for":[5,15,28],"artificial":[6],"neural":[7,11,153],"networks":[8,60],"called":[9,66],"Householder-absolute":[10],"layers,":[12,35],"or":[13,77,132],"Han-layers":[14,64,145],"short,":[16],"that":[17,75,120],"use":[18],"Householder":[19],"reflectors":[20],"as":[21,32],"weight":[22],"matrices":[23],"and":[24,44,51,182,184],"the":[25,53,125,134,147],"absolute-value":[26],"function":[27],"activation.":[29],"Han-layers,":[30],"functioning":[31],"fully":[33,112],"connected":[34,113],"are":[36,45,65,156,170],"motivated":[37],"by":[38,111,141],"recent":[39],"results":[40,89,169],"on":[41,91,116,164,176],"neural-network":[42],"variability":[43],"designed":[46],"to":[47,57,105,158,172,178,185],"increase":[48],"activation":[49],"ratio":[50],"reduce":[52,124],"chance":[54],"of":[55,127,136,150],"Collapse":[56],"Constants.":[58],"Neural":[59],"constructed":[61],"chiefly":[62],"from":[63],"HanNets.":[67],"By":[68],"construction,":[69],"HanNets":[70,100,121,177],"enjoy":[71],"theoretical":[73],"guarantee":[74],"vanishing":[76],"exploding":[78],"gradient":[79],"never":[80],"occurs.":[81],"conduct":[83],"several":[84],"proof-of-concept":[85,168],"experiments.":[86],"Some":[87],"surprising":[88],"obtained":[90],"styled":[92],"test":[93],"problems":[94],"suggest":[95],"that,":[96],"under":[97],"certain":[98],"conditions,":[99],"exhibit":[101],"an":[102],"unusual":[103],"ability":[104],"produce":[106],"nearly":[107],"perfect":[108],"solutions":[109],"unattainable":[110],"networks.":[114],"Experiments":[115],"regression":[117],"datasets":[118],"show":[119],"can":[122],"significantly":[123],"number":[126],"model":[128],"parameters":[129],"while":[130],"maintaining":[131],"improving":[133],"level":[135],"generalization":[137],"accuracy.":[138],"In":[139],"addition,":[140],"adding":[142],"few":[144],"into":[146],"pre-classification":[148],"FC-layer":[149],"convolutional":[152],"network,":[154],"we":[155],"able":[157],"quickly":[159],"improve":[160],"state-of-the-art":[162],"result":[163],"CIFAR10":[165],"dataset.":[166],"These":[167],"sufficient":[171],"necessitate":[173],"further":[174],"studies":[175],"understand":[179],"their":[180,187],"capacities":[181],"limits,":[183],"exploit":[186],"potentials":[188],"in":[189],"real-world":[190],"applications.":[191]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-06-22T00:00:00"}