{"id":"https://openalex.org/W7164343788","doi":"https://doi.org/10.48550/arxiv.2606.11341","title":"Energy-Conserved Neural Pipelines: Attenuating Error Propagation in Modular Neural Networks via Physical Conservation Constraints","display_name":"Energy-Conserved Neural Pipelines: Attenuating Error Propagation in Modular Neural Networks via Physical Conservation Constraints","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W7164343788","doi":"https://doi.org/10.48550/arxiv.2606.11341"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11341","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.11341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138448576","display_name":"David Young","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Young, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138419056","display_name":"Swan Yi Htet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Htet, Swan Yi","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/T11948","display_name":"Machine Learning in Materials Science","score":0.2671999931335449,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.2671999931335449,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.21040000021457672,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.11209999769926071,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.5961999893188477},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5809999704360962},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5713000297546387},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5066999793052673},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.49380001425743103},{"id":"https://openalex.org/keywords/energy-conservation","display_name":"Energy conservation","score":0.47609999775886536},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4729999899864197},{"id":"https://openalex.org/keywords/conservation-of-energy","display_name":"Conservation of energy","score":0.43459999561309814},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.3930000066757202}],"concepts":[{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5809999704360962},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5713000297546387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5285999774932861},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5066999793052673},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C520301825","wikidata":"https://www.wikidata.org/wiki/Q380170","display_name":"Energy conservation","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C52957995","wikidata":"https://www.wikidata.org/wiki/Q11382","display_name":"Conservation of energy","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36410000920295715},{"id":"https://openalex.org/C123614077","wikidata":"https://www.wikidata.org/wiki/Q1364905","display_name":"Propagation of uncertainty","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C27753989","wikidata":"https://www.wikidata.org/wiki/Q284885","display_name":"Superposition principle","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11341","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.11341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11341","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.4525056779384613,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modular":[0],"neural":[1],"network":[2,62],"pipelines":[3,102],"suffer":[4],"from":[5],"error":[6],"compounding:":[7],"noise":[8,87,113,129,203,210],"at":[9,48,86,107,114,156,161],"any":[10],"module":[11,50],"boundary":[12],"propagates":[13],"and":[14,93,127],"potentially":[15],"amplifies":[16],"through":[17,110],"subsequent":[18],"modules.":[19],"We":[20],"introduce":[21],"energy":[22,34,54,65,204],"conservation":[23,56,80,142,189],"as":[24],"a":[25,132,169],"hard":[26],"physical":[27],"constraint":[28],"on":[29,76,135,139,168,182,195],"inter-module":[30],"information":[31],"flow.":[32],"Activation":[33],"(the":[35],"squared":[36],"L2":[37],"norm":[38],"of":[39,83],"feature":[40],"vectors)":[41],"is":[42,57,205],"enforced":[43],"to":[44,121],"be":[45],"exactly":[46],"preserved":[47],"every":[49,115],"boundary.":[51],"Unlike":[52],"soft":[53],"penalties,":[55],"an":[58],"inviolable":[59],"law:":[60],"the":[61,118,141,166],"may":[63],"redistribute":[64],"across":[66],"neurons":[67],"but":[68],"cannot":[69],"create":[70],"or":[71],"destroy":[72],"it.":[73],"Four":[74],"experiments":[75],"CIFAR-10":[77],"demonstrate:":[78],"(1)":[79],"retains":[81],"77.4%":[82],"clean":[84],"accuracy":[85],"sigma=0.2,":[88,157],"versus":[89],"35.1%":[90],"for":[91,95],"baselines":[92],"30.9%":[94],"energy-penalized":[96],"models":[97],"(p<0.001,":[98],"5":[99,111,164],"seeds);":[100],"(2)":[101],"become":[103],"depth-invariant,":[104],"retaining":[105],"93.3%":[106],"depths":[108],"2":[109],"with":[112,131,146,151],"boundary;":[116],"(3)":[117],"advantage":[119,143,194],"generalizes":[120],"systematic":[122],"bias":[123],"(+45.1%),":[124],"Gaussian":[125],"(+40.4%),":[126],"adversarial":[128],"(+4.8%),":[130],"principled":[133],"non-effect":[134],"dropout":[136],"(-0.3%);":[137],"(4)":[138],"ResNet-18,":[140],"scales":[144],"inversely":[145],"intrinsic":[147],"normalization:":[148],"+0.3":[149],"pp":[150,154,160,192],"BatchNorm,":[152],"+26.2":[153],"without":[155],"reaching":[158],"+58.0":[159],"sigma=0.5.":[162],"Experiment":[163],"validates":[165],"operator":[167],"real":[170],"modular":[171],"robotic":[172],"pipeline":[173],"(MuJoCo":[174],"physics,":[175],"Franka":[176],"Panda).":[177],"Across":[178],"three":[179],"independent":[180],"runs":[181],"separate":[183],"machines":[184],"(90":[185],"trials":[186],"per":[187],"cell),":[188],"provides":[190],"+18.9":[191],"average":[193],"monocular-depth-style":[196],"noise.":[197],"A":[198],"formal":[199],"bound":[200],"proves":[201],"conserved":[202],"strictly":[206],"less":[207],"than":[208],"input":[209],"energy.":[211]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-12T00:00:00"}