{"id":"W2973163720","doi":"10.48550/arxiv.1907.10134","title":"BPPSA: Scaling Back-propagation by Parallel Scan Algorithm","year":2019,"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":"University of Toronto","funders":"","keywords":"Speedup; Scalability; Computer science; Recurrent neural network; Algorithm; Context (archaeology); Massively parallel; Parallel computing; Sequence (biology); Scaling; Dependency (UML); Artificial neural network; Computation; Backpropagation; Scale (ratio); Parallel algorithm; Artificial intelligence; Mathematics","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":[0.001211077,0.001575547,0.001121743,0.0008747394,0.0006590205,0.001231003,0.002547096,0.001333306,0.006965705],"category_scores_gemma":[0.006097507,0.0007169706,0.001128971,0.0009764573,0.0009081829,0.002515509,0.001763999,0.00250587,0.003716881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009430233,"about_ca_system_score_gemma":0.00268603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01093286,"about_ca_topic_score_gemma":0.01360519,"domain_scores_codex":[0.9990488,0.0001794722,0.00006514524,0.0002016979,0.0004054022,0.00009951963],"domain_scores_gemma":[0.9977806,0.0008880992,0.0001157952,0.000526093,0.0005979961,0.00009131365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006522972,0.0002863187,0.002136703,0.0002547238,0.0002222709,0.0002141458,0.0001744678,0.4145423,0.0160464,0.01420812,0.02114243,0.5301198],"study_design_scores_gemma":[0.0000358015,0.00003866981,0.00008381261,0.000006161591,0.00001346316,0.00002614864,0.00001359395,0.9897057,0.00304583,0.005361455,0.001661846,0.000007556678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02207078,0.0004568326,0.9547876,0.0004393723,0.0002649252,0.0001239601,0.0001975362,0.01706512,0.004593871],"genre_scores_gemma":[0.2142285,0.0003543492,0.7758925,0.0004055662,0.0001387582,0.0004640611,0.0009354627,0.00181469,0.005766168],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01093286,"threshold_uncertainty_score":0.02330256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04962296866302508,"score_gpt":0.1965533259730458,"score_spread":0.1469303573100207,"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."}}