{"id":"https://openalex.org/W7220649947","doi":"https://doi.org/10.48550/arxiv.2610.04697","title":"Efficiency and robustness partition the solution space for memory in recurrent networks","display_name":"Efficiency and robustness partition the solution space for memory in recurrent networks","publication_year":2026,"publication_date":"2026-10-03","ids":{"openalex":"https://openalex.org/W7220649947","doi":"https://doi.org/10.48550/arxiv.2610.04697"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.04697","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04697","pdf_url":"https://arxiv.org/pdf/2610.04697","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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.04697","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075317367","display_name":"William Qian","orcid":"https://orcid.org/0009-0001-8766-5739","observed_orcids":["https://orcid.org/0009-0001-8766-5739"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, William","raw_affiliation_strings":["Biophysics Graduate Program","Kempner Institute for the Study of Natural and Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biophysics Graduate Program","institution_ids":[]},{"raw_affiliation_string":"Kempner Institute for the Study of Natural and Artificial Intelligence","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023195984","display_name":"Cengiz Pehlevan","orcid":"https://orcid.org/0000-0001-9767-6063","observed_orcids":["https://orcid.org/0000-0001-9767-6063"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pehlevan, Cengiz","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":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/T10581","display_name":"Neural dynamics and brain function","score":0.8026999831199646,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.8026999831199646,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.16110000014305115,"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/T10448","display_name":"Memory and Neural Mechanisms","score":0.02290000021457672,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.9950000047683716},{"id":"https://openalex.org/keywords/solution-space","display_name":"solution space","score":0.8539999723434448},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.7319999933242798},{"id":"https://openalex.org/keywords/weight-efficiency","display_name":"weight efficiency","score":0.8830000162124634},{"id":"https://openalex.org/keywords/activity-efficiency","display_name":"activity efficiency","score":0.9710000157356262},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.9800000190734863},{"id":"https://openalex.org/keywords/transient-amplification","display_name":"transient amplification","score":0.6880000233650208},{"id":"https://openalex.org/keywords/premotor-cortex","display_name":"premotor cortex","score":0.9649999737739563}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6528000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6008999943733215},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.41339999437332153},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.40880000591278076},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34279999136924744},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3179999887943268},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2606000006198883},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.04697","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04697","pdf_url":"https://arxiv.org/pdf/2610.04697","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.04697","doi":"https://doi.org/10.48550/arxiv.2610.04697","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.04697","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.04697","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04697","pdf_url":"https://arxiv.org/pdf/2610.04697","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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220649947.pdf","grobid_xml":"https://content.openalex.org/works/W7220649947.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3212179912","https://openalex.org/W4385715981","https://openalex.org/W4412803987","https://openalex.org/W7171346293","https://openalex.org/W3048749966","https://openalex.org/W4415332068","https://openalex.org/W2770126130","https://openalex.org/W7133347577","https://openalex.org/W4206581007","https://openalex.org/W7119830644"],"abstract_inverted_index":{"In":[0],"computational":[1],"neuroscience,":[2],"task-trained":[3,101],"recurrent":[4,19,67],"neural":[5,68],"networks":[6,29,69,102],"(RNNs)":[7],"are":[8,30,158],"commonly":[9],"used":[10],"as":[11],"a":[12,24,54,91,130,170],"testbed":[13],"for":[14],"exploring":[15],"the":[16,63,73,97],"space":[17,65],"of":[18,41,66,75,100,136,173],"circuit":[20],"solutions":[21,89,116,128],"compatible":[22],"with":[23,39,96],"particular":[25],"function.":[26],"However,":[27],"these":[28,166],"subject":[31],"to":[32,82],"inductive":[33,98],"biases":[34,99],"that":[35,86,94,117,125,140,152],"may":[36],"be":[37],"misaligned":[38,174],"those":[40,139],"biological":[42],"circuits,":[43],"which":[44],"operate":[45],"under":[46],"various":[47],"efficiency":[48,113,157],"and":[49,80,103,138,155],"robustness":[50,81,154],"constraints.":[51],"Here,":[52],"using":[53],"minimal":[55],"stimulus":[56],"recall":[57],"task,":[58],"we":[59,123,150,168],"systematically":[60],"characterize":[61],"how":[62],"solution":[64],"is":[70],"shaped":[71],"by":[72],"desiderata":[74],"weight":[76,87],"efficiency,":[77,79],"activity":[78,112,126,137,156],"noise.":[83],"We":[84],"show":[85],"efficient":[88,127],"exhibit":[90,129],"low-rank":[92],"bias":[93],"aligns":[95],"favors":[104],"dynamical":[105],"motifs":[106],"involving":[107],"slow,":[108],"persistent":[109],"dynamics,":[110],"whereas":[111],"encourages":[114],"high-rank":[115],"rely":[118],"on":[119],"transient":[120],"amplification.":[121],"Moreover,":[122],"find":[124],"strong":[131],"dissociation":[132],"between":[133],"high-variance":[134],"modes":[135],"causally":[141],"influence":[142],"network":[143],"output.":[144],"Unlike":[145],"in":[146,160,179],"static":[147],"feedforward":[148],"settings,":[149],"demonstrate":[151],"noise":[153],"generally":[159],"opposition,":[161],"rather":[162],"than":[163],"synergistic.":[164],"Using":[165],"findings,":[167],"propose":[169],"normative":[171],"account":[172],"coding":[175],"phenomena":[176],"recently":[177],"identified":[178],"premotor":[180],"cortex.":[181]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-07T00:00:00"}