{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002313052,0.00006049103,0.00007215801,0.00003402113,0.00004468405,0.00002285557,0.0003651413,0.00006015817,0.0002770293],"category_scores_gemma":[0.00001509239,0.00005679151,0.00002249951,0.0002301236,0.00001537586,0.000492378,0.0001022333,0.0001627356,0.00008252611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003024257,"about_ca_system_score_gemma":0.00001408968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002956368,"about_ca_topic_score_gemma":0.000001806216,"domain_scores_codex":[0.9991118,0.00007338036,0.0001275384,0.0002395856,0.0003326965,0.0001149562],"domain_scores_gemma":[0.9993093,0.0000580049,0.0000727537,0.0004176385,0.0001002649,0.0000420531],"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":[0.000004782189,0.0001974211,0.002726551,0.000003567529,0.000008049752,2.306683e-7,0.001538095,0.3493303,0.0753083,0.2717487,0.00003523647,0.2990988],"study_design_scores_gemma":[0.0001506623,0.00008823575,0.001296741,0.00000317972,0.000002208153,0.000001489446,0.0001289252,0.9672245,0.0259598,0.004915053,0.0001534259,0.00007573024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4214916,0.00009146007,0.5717845,0.00006474282,0.0000832092,0.0002108081,4.3628e-8,0.0000837108,0.006189897],"genre_scores_gemma":[0.922635,0.000001367318,0.07713279,0.00009059355,0.00002188535,0.00002528615,0.000002399429,0.000004615849,0.00008609063],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6178942,"threshold_uncertainty_score":0.3033276,"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."}}