{"id":"W3201298227","doi":"10.1155/2021/3839543","title":"Pipelined Training with Stale Weights in Deep Convolutional Neural Networks","year":2021,"lang":"en","type":"article","venue":"Applied Computational Intelligence and Soft Computing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Backpropagation; Convolutional neural network; Inference; Parallel computing; FLOPS; Residual neural network; Artificial neural network; Computer engineering; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005921752,0.000810268,0.000379539,0.0004942231,0.0003891439,0.0006095141,0.00143575,0.0006105146,0.002989182],"category_scores_gemma":[0.001839249,0.0006088101,0.0004663483,0.0006464432,0.0006198419,0.00195276,0.0007467385,0.001274431,0.0007713892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00102797,"about_ca_system_score_gemma":0.001589633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01027038,"about_ca_topic_score_gemma":0.0204919,"domain_scores_codex":[0.9996786,0.00004619969,0.0000257627,0.00009050863,0.0001039498,0.00005499409],"domain_scores_gemma":[0.9993789,0.0002266013,0.00006352813,0.0001758402,0.0001251885,0.00002994187],"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":[0.0005607075,0.0002772305,0.002885288,0.0002138858,0.0001159283,0.0002496375,0.0002772789,0.4801018,0.0692335,0.01182766,0.007820082,0.426437],"study_design_scores_gemma":[0.00001929719,0.0001122556,0.0003885943,0.00001054756,0.00001291643,0.00003738013,0.00001360505,0.9686307,0.02564354,0.003041821,0.002076582,0.0000127872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1309915,0.0006599689,0.8537714,0.0002658989,0.0001136961,0.00009659467,0.0002402352,0.01057906,0.003281708],"genre_scores_gemma":[0.5993994,0.0003467932,0.3933361,0.0001994611,0.00003439521,0.000126032,0.0006316965,0.0004109027,0.005515294],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01027038,"threshold_uncertainty_score":0.02042121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02605909637599875,"score_gpt":0.2601603845405354,"score_spread":0.2341012881645366,"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."}}