{"id":"W2252795377","doi":"10.1007/s11227-016-1633-y","title":"GPU-enabled back-propagation artificial neural network for digit recognition in parallel","year":2016,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakehead University","funders":"Fundo para o Desenvolvimento das Ciências e da Tecnologia; Universidade de Macau","keywords":"Computer science; CUDA; Programmer; Artificial neural network; Graphics processing unit; Graphics; Parallel computing; Code (set theory); Central processing unit; General-purpose computing on graphics processing units; GPU cluster; Backpropagation; Computer architecture; Computer hardware; Computer engineering; Artificial intelligence; Embedded system; Computer graphics (images); Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.000979655,0.0001183976,0.0001880423,0.00007547074,0.0001991578,0.00006574369,0.0006344893,0.00004162848,0.000005406116],"category_scores_gemma":[0.0001085438,0.00006869283,0.00008295693,0.0004134391,0.00004305598,0.000870509,0.000105872,0.0001714165,0.00001931827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007016856,"about_ca_system_score_gemma":0.00003718159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003264956,"about_ca_topic_score_gemma":0.00001125904,"domain_scores_codex":[0.9985275,0.0001537155,0.0006243826,0.0001573745,0.0001906328,0.0003464365],"domain_scores_gemma":[0.9981397,0.001063826,0.0003171102,0.0002276708,0.0001919596,0.00005978004],"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":[0.0001663165,0.00007320348,0.0007615807,0.00001251678,0.00001944813,0.000005951272,0.0005098253,0.1449011,0.01325156,0.004287743,0.001420049,0.8345907],"study_design_scores_gemma":[0.002502068,0.0005497548,0.005171114,0.0006094039,0.00004198761,0.0004606061,0.0001400938,0.6733356,0.007144644,0.3075045,0.001959239,0.0005809969],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2795927,0.00005519587,0.7160042,0.003783813,0.000263399,0.0002386932,9.891967e-7,0.0000221952,0.00003882105],"genre_scores_gemma":[0.9157739,0.00003438236,0.08292557,0.0002648204,0.0009611851,0.000006116688,0.000001394287,0.00001303519,0.00001955615],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8340097,"threshold_uncertainty_score":0.2801212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04758717951977916,"score_gpt":0.2692865641119924,"score_spread":0.2216993845922132,"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."}}