{"id":"W2970610469","doi":"10.1109/bigdatacongress.2019.00034","title":"DLBench: An Experimental Evaluation of Deep Learning Frameworks","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Deep learning; Computer science; Benchmarking; Popularity; Artificial intelligence; Machine learning; Data science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007055008,0.003571273,0.001345318,0.003226905,0.001077062,0.001881994,0.007150439,0.002587873,0.00619871],"category_scores_gemma":[0.01855202,0.0008529681,0.001160902,0.003114669,0.001460069,0.003814251,0.002672377,0.002658989,0.002548331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002392721,"about_ca_system_score_gemma":0.002406409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01550446,"about_ca_topic_score_gemma":0.01624857,"domain_scores_codex":[0.9928339,0.002018334,0.0009565273,0.00123585,0.002219774,0.0007357382],"domain_scores_gemma":[0.988917,0.005235116,0.0005988461,0.001658581,0.002829661,0.0007607439],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0127424,0.01230292,0.02065664,0.009887637,0.002005808,0.001153622,0.0007778762,0.254072,0.04380026,0.01464625,0.1934838,0.4344707],"study_design_scores_gemma":[0.003183151,0.005305245,0.01143936,0.0005690247,0.0003850585,0.0006928075,0.0006474063,0.8617174,0.06113314,0.008252518,0.04643071,0.000244131],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7630812,0.01615685,0.09345725,0.002162779,0.003020908,0.003060197,0.03143532,0.05707627,0.03054924],"genre_scores_gemma":[0.7002446,0.003686487,0.2047024,0.001174276,0.0003068165,0.001755336,0.07360596,0.003984443,0.01053965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.992945,"threshold_uncertainty_score":0.0373109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03080481787692442,"score_gpt":0.3341198502469274,"score_spread":0.303315032370003,"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."}}