{"id":"W3170809304","doi":"10.48550/arxiv.2106.06401","title":"Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous\\n Distributed Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Concordia University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Asynchronous communication; Computer science; Greedy algorithm; Asynchronous learning; Artificial intelligence; Theoretical computer science; Distributed computing; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000183519,0.0003054598,0.0004691717,0.0001416879,0.0003393524,0.00009678461,0.0009461122,0.000230166,0.000009977988],"category_scores_gemma":[0.0001322256,0.0003886692,0.0001855395,0.0006072635,0.0001487297,0.0003056406,0.001855557,0.0007185536,0.000003603764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001773262,"about_ca_system_score_gemma":0.0001898873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004377222,"about_ca_topic_score_gemma":0.00003923567,"domain_scores_codex":[0.9979869,0.0001197635,0.0002762555,0.001149622,0.00007932391,0.0003881749],"domain_scores_gemma":[0.9978627,0.0004696382,0.0004864584,0.000737015,0.0002868971,0.0001572699],"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":[0.00001763995,0.00006109801,0.005023975,0.0001476461,0.00008808084,0.00004001102,0.0001774812,0.9471177,0.0003183436,0.04412541,0.00001636802,0.002866218],"study_design_scores_gemma":[0.0005101042,0.000115089,0.00191844,0.0001200145,0.00008303649,0.000009519253,0.0001736158,0.9887587,0.0003309738,0.007137248,0.0004407686,0.0004024361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2737064,0.0001944616,0.7253173,0.00005075699,0.00009813361,0.0003603689,0.00001280031,0.0001789027,0.00008082674],"genre_scores_gemma":[0.981459,0.000444065,0.01769008,0.00001515303,0.00005008013,0.000007779328,0.0001318029,0.00002612509,0.0001759604],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7077525,"threshold_uncertainty_score":0.9998565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03883672623548102,"score_gpt":0.2018811241617418,"score_spread":0.1630443979262608,"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."}}