{"id":"W4388481381","doi":"10.48550/arxiv.2106.06401","title":"Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Concordia University","funders":"","keywords":"Asynchronous communication; Computer science; Asynchronous learning; Greedy algorithm; Artificial intelligence; Machine learning; Algorithm; Computer network; Mathematics; Synchronous learning; Cooperative learning; Mathematics education; Teaching method","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001393155,0.0009946114,0.0009010281,0.000394503,0.0004243432,0.0009484713,0.002142695,0.001232645,0.003688424],"category_scores_gemma":[0.004222816,0.0005596125,0.000515923,0.0005157681,0.001127803,0.001884356,0.001788361,0.001379307,0.0006720351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001348105,"about_ca_system_score_gemma":0.001767968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003713147,"about_ca_topic_score_gemma":0.007221785,"domain_scores_codex":[0.999373,0.0001546327,0.00003091859,0.0001949338,0.0001422302,0.000104193],"domain_scores_gemma":[0.9989576,0.0005058424,0.00009456775,0.0002111699,0.0001456213,0.000085175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000264851,0.0001008625,0.0006460485,0.0000915022,0.00004946437,0.0001105328,0.00007818034,0.8825871,0.004973536,0.03246517,0.002920482,0.07571229],"study_design_scores_gemma":[0.00001890998,0.00001581326,0.0000366741,0.00000258768,0.000003519154,0.000008200393,0.000004366117,0.9901905,0.0005846217,0.008850714,0.0002815025,0.000002576613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0266352,0.0002897182,0.9684218,0.0003330283,0.00007055011,0.00006775395,0.00008547969,0.001244,0.002852512],"genre_scores_gemma":[0.7304478,0.0002196074,0.261536,0.0003247129,0.00009684493,0.0003313059,0.0002507087,0.0002550468,0.00653814],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003713147,"threshold_uncertainty_score":0.012339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03723864034099048,"score_gpt":0.1902064561983528,"score_spread":0.1529678158573623,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}