{"id":"https://openalex.org/W4405254279","doi":"https://doi.org/10.48550/arxiv.2412.06545","title":"On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks","display_name":"On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks","publication_year":2024,"publication_date":"2024-12-09","ids":{"openalex":"https://openalex.org/W4405254279","doi":"https://doi.org/10.48550/arxiv.2412.06545"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2412.06545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.06545","pdf_url":"https://arxiv.org/pdf/2412.06545","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.06545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010838126","display_name":"William T. Redman","orcid":"https://orcid.org/0000-0002-4147-2026"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Redman, William T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048522863","display_name":"Zhangyang Wang","orcid":"https://orcid.org/0000-0002-2050-5693"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhangyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047108263","display_name":"Alessandro Ingrosso","orcid":"https://orcid.org/0000-0001-5430-7559"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ingrosso, Alessandro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057039281","display_name":"Sebastian Goldt","orcid":"https://orcid.org/0000-0002-5799-7644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goldt, Sebastian","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":false,"cited_by_count":0,"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":0.9973999857902527,"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":0.9973999857902527,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9793000221252441,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.8007259368896484},{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.7893009185791016},{"id":"https://openalex.org/keywords/receptive-field","display_name":"Receptive field","score":0.6960049271583557},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5775882005691528},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5179242491722107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45566362142562866},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36576369404792786},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32431337237358093},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14006251096725464},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07694658637046814},{"id":"https://openalex.org/keywords/botany","display_name":"Botany","score":0.06568333506584167},{"id":"https://openalex.org/keywords/astrophysics","display_name":"Astrophysics","score":0.04313671588897705}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8007259368896484},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.7893009185791016},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.6960049271583557},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5775882005691528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5179242491722107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45566362142562866},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36576369404792786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32431337237358093},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14006251096725464},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07694658637046814},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.06568333506584167},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.04313671588897705}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2412.06545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.06545","pdf_url":"https://arxiv.org/pdf/2412.06545","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.06545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.06545","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.06545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.06545","pdf_url":"https://arxiv.org/pdf/2412.06545","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2376418092","https://openalex.org/W2089544495","https://openalex.org/W2079003682","https://openalex.org/W1555021777","https://openalex.org/W2913266608","https://openalex.org/W1964918325","https://openalex.org/W2072983018","https://openalex.org/W2799648451","https://openalex.org/W2189496153","https://openalex.org/W2186491718"],"abstract_inverted_index":{"Since":[0],"its":[1,29],"use":[2],"in":[3,106,135,242],"the":[4,31,35,75,107,130,143,181,187,190,204,210,219,223,228,231,247],"Lottery":[5],"Ticket":[6],"Hypothesis,":[7],"iterative":[8],"magnitude":[9],"pruning":[10],"(IMP)":[11],"has":[12],"become":[13],"a":[14,82,150,176],"popular":[15],"method":[16,178],"for":[17,167,179],"extracting":[18,49],"sparse":[19],"subnetworks":[20,50],"that":[21,33,44,55,64,92,114,139,153,160,200],"can":[22,245],"be":[23],"trained":[24],"to":[25,67,74,128,169,198,209,221],"high":[26],"performance.":[27,57],"Despite":[28],"success,":[30],"mechanism":[32],"drives":[34],"success":[36],"of":[37,48,77,84,132,146,183,189,206,212,225,230,233,249],"IMP":[38,45,66,101,140,168,201,226,244],"remains":[39,98],"unclear.":[40],"One":[41],"possibility":[42],"is":[43,46,126,218],"capable":[47],"with":[51,119],"good":[52],"inductive":[53,251],"biases":[54],"facilitate":[56],"Supporting":[58],"this":[59],"idea,":[60],"recent":[61],"work":[62],"showed":[63],"applying":[65],"fully":[68],"connected":[69],"neural":[70,90,234],"networks":[71,91],"(FCNs)":[72],"leads":[73],"emergence":[76,131],"local":[78,133],"receptive":[79],"fields":[80],"(RFs),":[81],"feature":[83],"mammalian":[85],"visual":[86],"cortex":[87],"and":[88],"convolutional":[89],"facilitates":[93],"image":[94],"processing.":[95],"However,":[96],"it":[97],"unclear":[99],"why":[100],"would":[102],"uncover":[103],"localized":[104,171,213],"features":[105],"first":[108,159,220],"place.":[109],"Inspired":[110],"by":[111],"results":[112],"showing":[113],"training":[115],"on":[116,186,227,239],"synthetic":[117],"images":[118],"highly":[120],"non-Gaussian":[121,144,161],"statistics":[122,145,163,188,229],"(e.g.,":[123],"sharp":[124],"edges)":[125],"sufficient":[127],"drive":[129,246],"RFs":[134],"FCNs,":[136],"we":[137,157],"hypothesize":[138],"iteratively":[141],"increases":[142,203],"FCN":[147,191],"representations,":[148],"creating":[149],"feedback":[151],"loop":[152],"enhances":[154],"localization.":[155],"Here,":[156],"demonstrate":[158],"input":[162],"are":[164],"indeed":[165],"necessary":[166],"discover":[170],"RFs.":[172,214],"We":[173],"then":[174],"develop":[175],"new":[177],"measuring":[180],"effect":[182,224],"individual":[184],"weights":[185],"representations":[192,232],"(\"cavity":[193],"method\"),":[194],"which":[195,217,243],"allows":[196],"us":[197],"show":[199],"systematically":[202],"non-Gaussianity":[205],"pre-activations,":[207],"leading":[208],"formation":[211,248],"Our":[215],"work,":[216],"study":[222],"networks,":[235],"sheds":[236],"parsimonious":[237],"light":[238],"one":[240],"way":[241],"strong":[250],"biases.":[252]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}