{"id":"W3083995206","doi":"10.5194/egusphere-egu2020-1963","title":"Entropy Ensemble Filter: Does information content assessment of bootstrapped training datasets before model training lead to better trade-off between ensemble size and predictive performance?","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Ensemble learning; Computer science; Ensemble forecasting; Machine learning; Artificial intelligence; Predictive modelling; Training set; Limiting; Artificial neural network; Entropy (arrow of time); Field (mathematics); Data mining; Mathematics; Engineering","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":[0.006544059,0.0007889332,0.001657772,0.001510503,0.0004911157,0.001775667,0.001390617,0.001861759,0.002222143],"category_scores_gemma":[0.02794658,0.000368163,0.0006882646,0.001018404,0.0007196602,0.004173802,0.001021331,0.001563552,0.0008022655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007731565,"about_ca_system_score_gemma":0.0008682623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002808376,"about_ca_topic_score_gemma":0.003363878,"domain_scores_codex":[0.9987019,0.0004235085,0.00007747101,0.0003104129,0.0003804252,0.0001062219],"domain_scores_gemma":[0.9909381,0.005963089,0.0004661252,0.00117673,0.001266162,0.0001898565],"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":[0.0009666063,0.0003319583,0.01554791,0.0003061981,0.000503832,0.0001852284,0.0002487156,0.2661489,0.01350807,0.0158758,0.01096742,0.6754094],"study_design_scores_gemma":[0.00002912368,0.0001563271,0.004951858,0.00008063129,0.00007396715,0.00007268359,0.00004113227,0.974391,0.008587324,0.009421208,0.002148343,0.00004643682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1379865,0.002073181,0.8487213,0.001775624,0.0003194218,0.0001255643,0.0005852519,0.002240623,0.006172432],"genre_scores_gemma":[0.8199403,0.001140493,0.1718963,0.0008196497,0.0004817374,0.0001721362,0.001452385,0.0005121504,0.003584818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006544059,"threshold_uncertainty_score":0.03460866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05990041339933667,"score_gpt":0.2811604212859233,"score_spread":0.2212600078865867,"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."}}