{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004199499,0.00022507,0.0003578649,0.000101705,0.0001561236,0.0001828988,0.0004995397,0.00007971209,0.00001061941],"category_scores_gemma":[0.0001124275,0.0001729912,0.00005145224,0.0002184433,0.00004659029,0.001963858,0.0002048747,0.0002727906,0.000005169979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003547069,"about_ca_system_score_gemma":0.0001160343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572533,"about_ca_topic_score_gemma":0.000005862038,"domain_scores_codex":[0.9981437,0.00007822992,0.0005884377,0.0004116046,0.0004377026,0.0003403091],"domain_scores_gemma":[0.9989186,0.0001510058,0.0002472016,0.0003924266,0.00005114679,0.0002396447],"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":[0.00007451319,0.00005071454,0.01858985,0.0002250231,0.0001258777,0.000002060988,0.06475595,0.007974408,0.01218851,0.004112378,0.001426028,0.8904747],"study_design_scores_gemma":[0.0006987542,0.00052175,0.07008944,0.0000471391,0.00002719654,0.000003077905,0.001187549,0.9239784,0.00150846,0.0001273108,0.001609272,0.0002016263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2738339,0.000004390298,0.717457,0.007190934,0.00004219609,0.0003262772,0.0003836033,0.0001222207,0.0006395409],"genre_scores_gemma":[0.9086925,0.000009210196,0.08896325,0.001545111,0.00006546157,0.00002867946,0.0006699174,0.000008954402,0.00001688195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.916004,"threshold_uncertainty_score":0.7054375,"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."}}