{"id":"W3092384192","doi":"10.48550/arxiv.2006.08305","title":"Inner Ensemble Networks: Average Ensemble as an Effective Regularizer","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Ensemble learning; Computer science; Ensemble forecasting; Artificial intelligence","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":[0.001737057,0.0009627223,0.001050846,0.0006765759,0.0004867147,0.0009312468,0.001804159,0.001112212,0.002536238],"category_scores_gemma":[0.003952361,0.0004799215,0.000859072,0.000781413,0.0007422433,0.002028802,0.00210161,0.002529787,0.0009586598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000602535,"about_ca_system_score_gemma":0.0009471903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002863479,"about_ca_topic_score_gemma":0.005936548,"domain_scores_codex":[0.9992025,0.000236159,0.00003764603,0.0001746921,0.0002541048,0.00009486566],"domain_scores_gemma":[0.9987922,0.0004117315,0.00009954998,0.0003540985,0.0002766971,0.00006577744],"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":[0.0001763008,0.0001154039,0.001484255,0.00009268612,0.000170403,0.00009528073,0.0001194048,0.7104087,0.006497901,0.04180124,0.008449532,0.2305888],"study_design_scores_gemma":[0.00000304525,0.00002046522,0.00007911091,0.000006992058,0.00000946873,0.00001747502,0.000004356386,0.9897887,0.001404182,0.007393176,0.001268213,0.0000048343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01369456,0.0003753054,0.981739,0.0001829727,0.00009176925,0.00002567056,0.0001080405,0.001023953,0.002758739],"genre_scores_gemma":[0.4381826,0.00071346,0.5469388,0.0005146922,0.0002907737,0.0002262799,0.0009327253,0.000851284,0.01134929],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002863479,"threshold_uncertainty_score":0.009186566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04090951258387337,"score_gpt":0.1958079585796569,"score_spread":0.1548984459957835,"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."}}