{"id":"W3035097696","doi":"10.24963/ijcai.2020/296","title":"Handling Black Swan Events in Deep Learning with Diversely Extrapolated Neural Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Hindsight bias; Deep learning; Artificial neural network; Set (abstract data type); Machine learning; Function (biology); Interpretability; Recurrent neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005615288,0.00007992103,0.0000827224,0.000037504,0.0001016345,0.00003998642,0.0002864382,0.00003834899,0.00002096424],"category_scores_gemma":[0.000004520684,0.00006766363,0.00002501642,0.0005764123,0.0000182319,0.0002146957,0.000103403,0.0002117945,0.00001270848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001418049,"about_ca_system_score_gemma":0.000007217723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004269735,"about_ca_topic_score_gemma":0.00002099417,"domain_scores_codex":[0.9993486,0.00002710927,0.0001217127,0.0002498967,0.00008948881,0.0001631625],"domain_scores_gemma":[0.9997134,0.00001771645,0.00004729091,0.0001180867,0.00002483295,0.00007866242],"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":[0.0000762405,0.0001372136,0.1269748,0.00001995884,0.00004227555,0.00004152,0.003486548,0.6834873,0.001349096,0.01753364,0.0002437122,0.1666077],"study_design_scores_gemma":[0.000170696,0.0001062398,0.005603807,0.000004683451,0.000001839945,0.000002745453,0.00006043679,0.9931949,0.0002804491,0.00005702809,0.0004186301,0.00009849864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07505494,0.00001388183,0.9230143,0.0006495154,0.00001106669,0.0001216471,5.418246e-8,0.0003875681,0.0007469905],"genre_scores_gemma":[0.9864411,0.00001049994,0.01304241,0.0003816432,0.0000233574,0.00001028485,0.00000106482,0.00000594604,0.00008369755],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9113861,"threshold_uncertainty_score":0.2759243,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01508044470271067,"score_gpt":0.2180856509858087,"score_spread":0.203005206283098,"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."}}