{"id":"https://openalex.org/W7164156216","doi":"https://doi.org/10.48550/arxiv.2606.09928","title":"Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment","display_name":"Forward-Only Convolutional Neural Networks with Learnable Channel-Class Assignment","publication_year":2026,"publication_date":"2026-06-07","ids":{"openalex":"https://openalex.org/W7164156216","doi":"https://doi.org/10.48550/arxiv.2606.09928"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.09928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09928","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":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.2606.09928","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138316208","display_name":"Mohammadnavid Ghader","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghader, Mohammadnavid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047019835","display_name":"Saeed Reza Kheradpisheh","orcid":"https://orcid.org/0000-0001-6168-4379"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kheradpisheh, Saeed Reza","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027858445","display_name":"Bahar Farahani","orcid":"https://orcid.org/0000-0002-7016-6853"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farahani, Bahar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043743959","display_name":"Mahmood Fazlali","orcid":"https://orcid.org/0000-0002-1701-5562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fazlali, Mahmood","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/T10036","display_name":"Advanced Neural Network Applications","score":0.38589999079704285,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.38589999079704285,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.15299999713897705,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.08479999750852585,"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/orthogonality","display_name":"Orthogonality","score":0.5687000155448914},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5442000031471252},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5407999753952026},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5170000195503235},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5123999714851379},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4510999917984009},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4490000009536743},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.42239999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6460000276565552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946000218391418},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.5687000155448914},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5170000195503235},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5123999714851379},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4603999853134155},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.42239999771118164},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.3817000091075897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.09928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09928","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":"doi:10.48550/arxiv.2606.09928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09928","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"Forward-Forward":[1],"(FF)":[2],"algorithm":[3],"offers":[4],"a":[5,51,77],"biologically":[6],"inspired":[7],"alternative":[8],"to":[9,26,40,70,115],"backpropagation":[10],"by":[11,65],"replacing":[12],"gradient-based":[13],"credit":[14],"assignment":[15,54],"with":[16,133],"local,":[17],"forward-only":[18,96,118,153],"objectives.":[19],"While":[20],"recent":[21],"extensions":[22],"have":[23],"adapted":[24],"FF":[25],"convolutional":[27,62],"neural":[28],"networks":[29],"(CNNs),":[30],"existing":[31,116],"formulations":[32],"rely":[33],"on":[34,88],"static":[35],"channel-class":[36,53],"partitions":[37],"and":[38,67,112,143],"struggle":[39],"perform":[41],"effectively":[42],"in":[43,155],"complex":[44],"tasks.":[45],"In":[46],"this":[47],"work,":[48],"we":[49],"introduce":[50],"learnable":[52,140],"mechanism":[55],"that":[56,82,138],"enables":[57],"adaptive,":[58],"data-driven":[59],"specialization":[60,142],"of":[61,95,152],"channels,":[63],"supported":[64],"entropy":[66],"orthogonality":[68],"regularization":[69],"promote":[71],"learning":[72,154],"performance.":[73],"We":[74],"further":[75],"propose":[76],"loss-aware":[78],"layer":[79,144],"contribution":[80,145],"strategy":[81],"adaptively":[83],"weights":[84],"intermediate-layer":[85],"predictions":[86],"based":[87],"their":[89],"validation":[90],"performance,":[91],"enhancing":[92],"the":[93,102,131,149],"effectiveness":[94],"inference.":[97],"Integrated":[98],"into":[99],"residual":[100],"CNNs,":[101],"proposed":[103],"method":[104],"achieves":[105],"consistently":[106],"superior":[107],"performance":[108,125],"across":[109],"CIFAR-10,":[110],"CIFAR-100,":[111],"Tiny-ImageNet":[113],"compared":[114],"similar":[117],"methods.":[119],"Notably,":[120],"it":[121],"establishes":[122],"new":[123],"state-of-the-art":[124],"among":[126],"FF-based":[127],"models,":[128],"substantially":[129],"narrowing":[130],"gap":[132],"backpropagation.":[134],"These":[135],"findings":[136],"demonstrate":[137],"introducing":[139],"channel":[141],"weighting":[146],"significantly":[147],"enhances":[148],"representational":[150],"capacity":[151],"deep":[156],"CNNs.":[157]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-11T00:00:00"}