{"id":"https://openalex.org/W3209188455","doi":null,"title":"Learnable weight initialization in neural networks","display_name":"Learnable weight initialization in neural networks","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3209188455","mag":"3209188455"},"language":"en","primary_location":{"id":"pmh:oai:tudelft.nl:uuid:615d5f26-7bb4-4a9a-807c-7fecf9d8c862","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:615d5f26-7bb4-4a9a-807c-7fecf9d8c862","pdf_url":"http://resolver.tudelft.nl/uuid:615d5f26-7bb4-4a9a-807c-7fecf9d8c862","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://resolver.tudelft.nl/uuid:615d5f26-7bb4-4a9a-807c-7fecf9d8c862","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aninda Bhattacharya","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aninda Bhattacharya","raw_affiliation_strings":[],"raw_orcid":null,"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":true,"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":0.7943999767303467,"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":0.7943999767303467,"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":0.0786999985575676,"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":0.07069999724626541,"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/weight-initialization","display_name":"weight initialization","score":0.9520000219345093},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.828000009059906},{"id":"https://openalex.org/keywords/linear-regression","display_name":"linear regression","score":0.5720000267028809},{"id":"https://openalex.org/keywords/activation-functions","display_name":"activation functions","score":0.8080000281333923},{"id":"https://openalex.org/keywords/relu","display_name":"ReLU","score":0.7360000014305115},{"id":"https://openalex.org/keywords/sigmoid","display_name":"sigmoid","score":0.8690000176429749},{"id":"https://openalex.org/keywords/hyperbolic-tangent","display_name":"hyperbolic tangent function","score":0.9739999771118164},{"id":"https://openalex.org/keywords/gradient-flow","display_name":"gradient flow","score":0.6959999799728394},{"id":"https://openalex.org/keywords/vanishing-and-exploding-gradients","display_name":"vanishing and exploding gradients","score":0.9520000219345093},{"id":"https://openalex.org/keywords/lenet","display_name":"LeNet","score":0.9549999833106995},{"id":"https://openalex.org/keywords/resnet-18","display_name":"ResNet-18","score":0.9580000042915344}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7362209558486938},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.7349476218223572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6813127398490906},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6609477400779724},{"id":"https://openalex.org/C38365724","wikidata":"https://www.wikidata.org/wiki/Q4677469","display_name":"Activation function","level":3,"score":0.639418363571167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6061005592346191},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5829759240150452},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.574420154094696},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4664095640182495},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45845121145248413},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.44897735118865967},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.44643720984458923},{"id":"https://openalex.org/C92047909","wikidata":"https://www.wikidata.org/wiki/Q204034","display_name":"Hyperbolic function","level":2,"score":0.4446653127670288},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4225604832172394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.376014769077301},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.231672465801239},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:tudelft.nl:uuid:615d5f26-7bb4-4a9a-807c-7fecf9d8c862","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:615d5f26-7bb4-4a9a-807c-7fecf9d8c862","pdf_url":"http://resolver.tudelft.nl/uuid:615d5f26-7bb4-4a9a-807c-7fecf9d8c862","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},{"id":"mag:3209188455","doi":null,"is_oa":false,"landing_page_url":"https://repository.tudelft.nl/islandora/object/uuid%3A615d5f26-7bb4-4a9a-807c-7fecf9d8c862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:615d5f26-7bb4-4a9a-807c-7fecf9d8c862","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:615d5f26-7bb4-4a9a-807c-7fecf9d8c862","pdf_url":"http://resolver.tudelft.nl/uuid:615d5f26-7bb4-4a9a-807c-7fecf9d8c862","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3209188455.pdf","grobid_xml":"https://content.openalex.org/works/W3209188455.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2178237821","https://openalex.org/W2194775991"],"related_works":["https://openalex.org/W3046894786","https://openalex.org/W2611453176","https://openalex.org/W7133275896","https://openalex.org/W3003013287","https://openalex.org/W7061648608","https://openalex.org/W2972760919","https://openalex.org/W4399676550","https://openalex.org/W4396230045","https://openalex.org/W2755231872","https://openalex.org/W7109085974"],"abstract_inverted_index":{"A":[0],"new":[1],"method":[2,14,136,211],"of":[3,34,66,118,126,144,147,231,246],"initializing":[4],"the":[5,32,35,43,48,58,64,67,71,93,103,115,124,138,145,148,163,170,182,188,195,204,215,220,223,227,243,247],"weights":[6,65,105,139,216,224],"in":[7,123,181],"deep":[8,127],"neural":[9],"networks":[10],"is":[11,45,75,130,152,159],"proposed.":[12],"The":[13,87,173,210],"follows":[15],"two":[16],"steps.":[17],"First,":[18],"consider":[19],"each":[20,54],"layer":[21,36,55],"as":[22],"a":[23,27,153,199],"model":[24,69],"and":[25,40,61,79,84,98,109,197,206],"perform":[26,107],"linear":[28],"regression":[29],"to":[30,38,51,57,91,132,140,161,168,184,213],"keep":[31],"mean":[33,60],"output":[37],"zero":[39],"variance":[41],"after":[42],"data":[44],"passed":[46],"through":[47,194],"activation":[49,88],"function":[50],"one.":[52],"Once":[53],"converges":[56],"target":[59],"variance,":[62],"initialize":[63],"original":[68],"with":[70],"learned":[72,104,142],"weights.":[73,172],"Performance":[74],"evaluated":[76],"on":[77,82],"LeNet":[78],"ResNet18":[80],"architectures":[81],"FashionMNIST":[83],"Imagenette":[85],"datasets.":[86],"functions":[89],"used":[90,121,180],"analyze":[92],"performance":[94,245],"are":[95],"sigmoid,":[96],"tanh":[97],"ReLU.":[99],"Findings":[100],"show":[101],"that":[102,134],"can":[106,178],"similarly,":[108],"for":[110,242],"certain":[111],"scenarios,":[112],"better":[113,185],"than":[114],"different":[116],"types":[117],"weight":[119],"initializers":[120],"frequently":[122],"field":[125],"learning.":[128],"It":[129],"important":[131],"mention":[133],"this":[135,176],"requires":[137,212],"be":[141,179,192,240],"independently":[143],"training":[146,219],"model.":[149],"Thus,":[150],"there":[151],"small":[154],"time":[155],"overhead.":[156],"Moreover,":[157],"it":[158],"required":[160],"adjust":[162],"hyperparameters(learning":[164,228],"rate,":[165,229],"epochs":[166],"etc)":[167],"find":[169],"optimal":[171,244],"findings":[174],"from":[175],"thesis":[177],"future":[183,235],"understand":[186],"how":[187],"gradient":[189,208],"flow":[190],"could":[191,239],"controlled":[193],"network":[196],"finding":[198],"more":[200],"generic":[201],"approach":[202],"towards":[203],"vanishing":[205],"exploding":[207],"problem.":[209],"learn":[214],"followed":[217],"by":[218],"network.":[221,248],"Learning":[222],"involves":[225],"tweaking":[226],"number":[230],"epochs,":[232],"etc).":[233],"For":[234],"work,":[236],"these":[237],"aspects":[238],"automated":[241]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-11-08T00:00:00"}