{"id":"W2964330541","doi":"10.1109/iiswc.2018.8573476","title":"Benchmarking and Analyzing Deep Neural Network Training","year":2018,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":157,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Toronto","funders":"","keywords":"Computer science; Toolchain; Artificial intelligence; Machine learning; Benchmarking; Deep learning; Artificial neural network; Inference; Benchmark (surveying); Reinforcement learning; Convolutional neural network; Profiling (computer programming); Deep neural networks; Workspace; Robot; Software","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":[0.005520889,0.002708723,0.001104985,0.002151917,0.0006423111,0.001594676,0.003733609,0.001017174,0.002239502],"category_scores_gemma":[0.01772843,0.0006681816,0.0009431847,0.004274517,0.001101042,0.002794953,0.002063064,0.002004123,0.001084193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002227509,"about_ca_system_score_gemma":0.00210469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01011727,"about_ca_topic_score_gemma":0.009327265,"domain_scores_codex":[0.9924672,0.001842808,0.0008762531,0.001068394,0.002898912,0.0008464473],"domain_scores_gemma":[0.9899573,0.004117709,0.0004659208,0.002555425,0.002549435,0.000354232],"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":[0.001359621,0.0008282031,0.01441406,0.001452316,0.000492462,0.0004487226,0.0002654456,0.664059,0.01565824,0.01294139,0.04862656,0.239454],"study_design_scores_gemma":[0.0001010368,0.0004409088,0.005131257,0.00008106723,0.00004740408,0.00009570592,0.0001449148,0.9409482,0.03788908,0.006487797,0.008588867,0.00004381794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7716248,0.006981686,0.1512743,0.001232558,0.001024919,0.0004644569,0.01216606,0.03254597,0.0226853],"genre_scores_gemma":[0.8246101,0.002091275,0.1290492,0.0003952017,0.0001100477,0.0005529987,0.03593342,0.002862903,0.004394878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01011727,"threshold_uncertainty_score":0.02919763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01980527962653514,"score_gpt":0.2621856353086831,"score_spread":0.2423803556821479,"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."}}