{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004837003,0.000117854,0.0001379379,0.00006252172,0.0004044966,0.0002080138,0.0004285175,0.00004326679,0.00006063396],"category_scores_gemma":[0.00007220304,0.0001077583,0.00003000059,0.0004019221,0.00008757684,0.0005082259,0.0004419345,0.0001809789,0.000008876606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001512774,"about_ca_system_score_gemma":0.00001449675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002357058,"about_ca_topic_score_gemma":0.00004021268,"domain_scores_codex":[0.9988758,0.00007949954,0.0001605409,0.0003598347,0.0001433152,0.0003810342],"domain_scores_gemma":[0.9993801,0.0001621247,0.00006890413,0.0002619624,0.00003939166,0.00008748447],"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":[0.000004996529,0.000004827994,0.02668824,0.000004984819,0.00002370828,0.00001887757,0.003930977,0.05190229,0.00006586733,0.07657449,0.0001559757,0.8406247],"study_design_scores_gemma":[0.0001247248,0.00005231901,0.008063728,0.000009733179,0.000004621513,0.00002267201,0.00005823332,0.9887154,0.000008035932,0.002128593,0.0006674657,0.0001445201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02976975,0.0000750327,0.9596003,0.0003461943,0.0006160226,0.00004455871,2.615495e-8,0.0002076654,0.00934044],"genre_scores_gemma":[0.709132,0.000001466283,0.2896264,0.0003147156,0.0008752199,0.000001103141,3.218722e-7,0.000006324562,0.00004256271],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9368131,"threshold_uncertainty_score":0.4394254,"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."}}