{"id":"W3039588859","doi":"10.32920/24132885","title":"Towards Robust Deep Learning With Ensemble Networks and Noisy Layers","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Vector Institute; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Robustness (evolution); Adversarial system; Computer science; Artificial intelligence; Deep learning; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004328363,0.001939221,0.001408188,0.0008731959,0.0005937729,0.001671493,0.002345934,0.002801914,0.0021286],"category_scores_gemma":[0.0119189,0.001002121,0.0009260751,0.0006903901,0.002736075,0.004014203,0.006409163,0.006144789,0.0008210787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001304014,"about_ca_system_score_gemma":0.0007669879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001335456,"about_ca_topic_score_gemma":0.001234848,"domain_scores_codex":[0.9973815,0.0009036953,0.00009117281,0.0005083287,0.0008698829,0.0002454357],"domain_scores_gemma":[0.9941739,0.002969215,0.0005655377,0.00163893,0.0004728197,0.0001795419],"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":[0.0002521901,0.00007400482,0.0008480508,0.00008720663,0.0001592623,0.0001519346,0.0001046855,0.7984039,0.01002058,0.1114361,0.003641971,0.07482015],"study_design_scores_gemma":[0.000005765298,0.00002638143,0.0000522308,0.000008383988,0.000007027902,0.00002505351,0.000005627187,0.954328,0.002886066,0.04197741,0.0006718964,0.000006173246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009115912,0.0003159931,0.9874835,0.0004968905,0.0000446569,0.00001726713,0.00004104009,0.0006992686,0.001785426],"genre_scores_gemma":[0.6886373,0.0006096948,0.2992984,0.001128026,0.0002803773,0.0001499284,0.0003095537,0.0005411269,0.009045618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004328363,"threshold_uncertainty_score":0.02289081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02459965081981148,"score_gpt":0.2520518520576505,"score_spread":0.227452201237839,"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."}}