{"id":"W2943204979","doi":"10.1109/dsw.2019.8755559","title":"Introducing Graph Smoothness Loss for Training Deep Learning Architectures","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"","keywords":"Computer science; Robustness (evolution); Smoothness; Artificial intelligence; Cross entropy; Graph; Entropy (arrow of time); Deep learning; Machine learning; Algorithm; Pattern recognition (psychology); Theoretical computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001088435,0.0003644855,0.0004495114,0.0003724743,0.0002639594,0.0005919829,0.001821626,0.0002616412,0.00002235574],"category_scores_gemma":[0.0005868458,0.0003283218,0.0002230611,0.0002258577,0.00004902311,0.0001204996,0.001153328,0.001360217,0.00003255999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004598602,"about_ca_system_score_gemma":0.0001439522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001096596,"about_ca_topic_score_gemma":0.00003171058,"domain_scores_codex":[0.9971731,0.0002248632,0.0004152175,0.001373217,0.0003275718,0.0004860708],"domain_scores_gemma":[0.9974349,0.0005157402,0.0003804813,0.001437532,0.0001294988,0.0001018601],"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":[0.00001621223,0.00002677614,0.002004653,0.0003767165,0.00006289491,0.000002100499,0.004683207,0.4402355,0.0001596556,0.03135381,0.0002303106,0.5208482],"study_design_scores_gemma":[0.0003816994,0.00008413645,0.004723971,0.0001373866,0.00002565385,0.00001276439,0.0001800243,0.9582947,0.0001484656,0.01802877,0.01732782,0.0006546401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00866518,0.0002228627,0.9835261,0.002150516,0.001320715,0.0005222764,0.000006463728,0.0006957033,0.002890175],"genre_scores_gemma":[0.7734045,0.00002190533,0.2243494,0.0002190308,0.0004958193,0.0001190428,0.0002439295,0.00004038115,0.001105952],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7647393,"threshold_uncertainty_score":0.9999169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02606649194961226,"score_gpt":0.2828361543502212,"score_spread":0.256769662400609,"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."}}