{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00219322,0.001618428,0.0008472214,0.000934186,0.0003833004,0.001212316,0.001405412,0.002064841,0.001810311],"category_scores_gemma":[0.007695651,0.0005494758,0.0007685925,0.0008229751,0.001479038,0.00225972,0.002590323,0.003464739,0.0006302119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001056306,"about_ca_system_score_gemma":0.0009920988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001387372,"about_ca_topic_score_gemma":0.001437146,"domain_scores_codex":[0.9990702,0.000284244,0.00005440995,0.0001661268,0.00034389,0.00008120445],"domain_scores_gemma":[0.9982194,0.0009141359,0.0001708437,0.0003083021,0.0002879499,0.00009922398],"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":[0.0001771464,0.0001191915,0.001072306,0.0001064109,0.00006996464,0.0001199431,0.00005228508,0.8382605,0.01152932,0.06909852,0.003586583,0.07580782],"study_design_scores_gemma":[0.000007821289,0.0000423549,0.0001084881,0.000008355707,0.000005487667,0.00002066212,0.000002800654,0.9765968,0.001455918,0.02105207,0.0006927495,0.000006438705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01295134,0.0002015268,0.9847081,0.0003250427,0.00005063826,0.00002512668,0.0000794328,0.000509096,0.001149704],"genre_scores_gemma":[0.5996877,0.0006408188,0.3902804,0.0005472977,0.0002385339,0.0002853539,0.0007807587,0.0006424796,0.006896676],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00219322,"threshold_uncertainty_score":0.011599,"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."}}