{"id":"https://openalex.org/W7165635255","doi":"https://doi.org/10.48550/arxiv.2606.22744","title":"Error Highways: Scaling Predictive Coding to Very Deep Networks","display_name":"Error Highways: Scaling Predictive Coding to Very Deep Networks","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165635255","doi":"https://doi.org/10.48550/arxiv.2606.22744"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22744","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22744","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.22744","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139128461","display_name":"Amirhossein Mohammadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammadi, Amirhossein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134343263","display_name":"Alexander G. Ororbia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ororbia, Alexander G.","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.22660000622272491,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.22660000622272491,"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":0.13860000669956207,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.054499998688697815,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7020999789237976},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5766000151634216},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49050000309944153},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.47699999809265137},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.4406999945640564},{"id":"https://openalex.org/keywords/error-function","display_name":"Error function","score":0.415800005197525},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.40389999747276306},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.40209999680519104},{"id":"https://openalex.org/keywords/attenuation","display_name":"Attenuation","score":0.3919000029563904},{"id":"https://openalex.org/keywords/mean-squared-prediction-error","display_name":"Mean squared prediction error","score":0.36820000410079956}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7020999789237976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5879999995231628},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5831000208854675},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.4406999945640564},{"id":"https://openalex.org/C202286095","wikidata":"https://www.wikidata.org/wiki/Q579262","display_name":"Error function","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.40389999747276306},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C184652730","wikidata":"https://www.wikidata.org/wiki/Q2357982","display_name":"Attenuation","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36640000343322754},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C104759252","wikidata":"https://www.wikidata.org/wiki/Q187120","display_name":"Time shifting","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C170122806","wikidata":"https://www.wikidata.org/wiki/Q1914828","display_name":"Linear scale","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28049999475479126},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22744","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22744","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.22744","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22744","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":0.4313946068286896,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Predictive":[0],"coding":[1,77],"networks":[2],"(PCNs)":[3],"offer":[4],"a":[5,67,113],"biologically-plausible,":[6],"local-learning":[7],"alternative":[8],"to":[9,20,33,95,127,172,182],"back-propagation":[10],"of":[11,123,170],"errors":[12],"(backprop).":[13],"Nevertheless,":[14],"they":[15],"have":[16],"remained":[17],"largely":[18],"confined":[19],"shallow":[21],"architectures":[22],"and":[23,161],"evaluated":[24],"on":[25],"simple":[26],"machine":[27],"intelligence":[28],"benchmarks.":[29],"A":[30],"central":[31],"obstacle":[32],"scaling":[34],"PCNs":[35],"is":[36,103,121,178],"that":[37,69,89,141,165,177],"the":[38,48,71,96,106,109,131,135,148,153],"learning":[39],"signal":[40],"decays":[41,142],"rapidly":[42],"as":[43],"it":[44],"propagates":[45],"away":[46],"from":[47],"clamped":[49,97],"boundaries,":[50],"leaving":[51],"interior":[52],"layers":[53,174],"effectively":[54,167],"unchanged.":[55],"To":[56],"directly":[57,94],"counter":[58],"this":[59,101],"problem,":[60],"we":[61,163],"propose":[62],"highway":[63,110],"error":[64,133],"propagation":[65],"(HEP),":[66],"scheme":[68],"augments":[70],"free":[72],"energy":[73],"function":[74],"underlying":[75],"predictive":[76],"(PC)":[78],"by":[79],"altering":[80],"its":[81],"neural":[82],"structure":[83],"with":[84,139,175,180],"feedback":[85],"matrices":[86],"$V_{L\\to":[87],"i}$":[88],"couple":[90],"selected":[91],"hidden":[92,107,137],"states":[93],"output":[98,132],"error.":[99],"Since":[100],"coupling":[102],"linear":[104],"in":[105,125,144],"state,":[108],"pathway":[111],"delivers":[112],"correction":[114],"at":[115],"every":[116],"inference":[117],"step":[118],"whose":[119],"magnitude":[120],"independent":[122],"depth,":[124],"contrast":[126],"vanilla":[128],"PC":[129,155],"where":[130],"reaches":[134],"$i$-th":[136],"layer":[138],"attenuation":[140],"exponentially":[143],"depth.":[145,183],"This":[146],"bypasses":[147],"Jacobian":[149],"chain":[150],"while":[151],"preserving":[152],"local":[154],"synaptic":[156],"update":[157],"rule.":[158],"On":[159],"MNIST":[160],"Fashion-MNIST,":[162],"show":[164],"HEP":[166],"trains":[168],"MLPs":[169],"up":[171],"128":[173],"accuracy":[176],"robust":[179],"respect":[181]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}