{"id":"W2292678148","doi":"10.1109/nemo.2015.7415056","title":"Parallel back-propagation neural network training technique using CUDA on multiple GPUs","year":2015,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"CUDA; Computer science; Kernel (algebra); Parallel computing; Artificial neural network; Graphics; Backpropagation; Graphics processing unit; Coprocessor; Computational science; General-purpose computing on graphics processing units; Algorithm; Artificial intelligence; Computer graphics (images); 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":[0.0004979631,0.0007310981,0.0005880772,0.0004841912,0.0006395427,0.000803881,0.001554696,0.0005756225,0.004016278],"category_scores_gemma":[0.00161422,0.0004070763,0.00040089,0.0008460407,0.0003596771,0.0009723039,0.0005889943,0.001260303,0.0009720613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008021597,"about_ca_system_score_gemma":0.0014429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01501094,"about_ca_topic_score_gemma":0.0135399,"domain_scores_codex":[0.9996754,0.00005254135,0.00002234916,0.00006165519,0.0001491496,0.00003878157],"domain_scores_gemma":[0.9993544,0.000129966,0.00004502188,0.0001236492,0.0003152762,0.00003165525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003057829,0.0001359136,0.002133803,0.0002130531,0.0001367741,0.0003948499,0.0002548901,0.5237099,0.0370272,0.01875855,0.01486802,0.4020612],"study_design_scores_gemma":[0.00001168906,0.00001431402,0.0001177861,0.000003957718,0.000004977639,0.00002817919,0.000007706893,0.9905722,0.005886316,0.001019209,0.002328316,0.000005375258],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01431559,0.0001018517,0.9762023,0.0001878817,0.00008323535,0.00005265166,0.00006322677,0.004455429,0.004537892],"genre_scores_gemma":[0.2240634,0.0001554487,0.7673125,0.00008571906,0.00002586745,0.0002507811,0.0002233557,0.0003488094,0.007534111],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01501094,"threshold_uncertainty_score":0.02984715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.106902301021518,"score_gpt":0.2922494455424687,"score_spread":0.1853471445209507,"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."}}