{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001948605,0.0002417956,0.0002736532,0.0001122922,0.0003471026,0.0001667153,0.0003997457,0.00007058144,0.00000796635],"category_scores_gemma":[0.00001915521,0.0002414186,0.00004072117,0.0009862982,0.0001471131,0.0002620126,0.0002881463,0.0003589444,0.000007443002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005145776,"about_ca_system_score_gemma":0.0001223923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004832512,"about_ca_topic_score_gemma":0.00002373202,"domain_scores_codex":[0.9979208,0.00005386006,0.0004840839,0.000750897,0.0003302078,0.0004601473],"domain_scores_gemma":[0.9982571,0.001008736,0.0001553358,0.0002460608,0.0001974298,0.0001353432],"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":[0.000007691205,0.00003318273,0.0003223293,0.000004392279,0.000008890922,0.00002275389,0.0006012158,0.6993878,0.00001092293,0.1952051,0.000003912164,0.1043918],"study_design_scores_gemma":[0.0002145639,0.0000262079,0.002239201,0.00002698881,0.000004077273,0.0001397596,0.0002469256,0.9390815,0.00006824088,0.05759171,0.00008827455,0.0002724668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03226769,0.0003664196,0.9660874,0.0004406991,0.00008797333,0.0002001398,0.000001091504,0.0001551205,0.0003934474],"genre_scores_gemma":[0.7763866,0.00001101904,0.2227109,0.000705497,0.0001082827,0.00001808895,0.00003605039,0.00001305006,0.00001057038],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7441189,"threshold_uncertainty_score":0.9844763,"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."}}