{"id":"W6989518100","doi":"","title":"Balanced mixture of supernets for learning the CNN pooling architecture","year":2023,"lang":"en","type":"other","venue":"Espace ÉTS (ETS)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Pooling; Feature (linguistics); Architecture; Pattern recognition (psychology); Deep learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002491317,0.002668222,0.001350625,0.001081092,0.0005678025,0.0009537298,0.003097054,0.00158801,0.004361763],"category_scores_gemma":[0.003833955,0.001261041,0.001514077,0.0009945622,0.0008000477,0.003777967,0.0025871,0.002574896,0.002181766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001343304,"about_ca_system_score_gemma":0.001307215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003747781,"about_ca_topic_score_gemma":0.009663332,"domain_scores_codex":[0.9992518,0.0001981042,0.00004677533,0.0002828318,0.0001145086,0.0001060016],"domain_scores_gemma":[0.9993454,0.0001763022,0.00005813639,0.0002239478,0.0001214925,0.0000747385],"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":[0.001358583,0.0003426007,0.005229278,0.0002069372,0.0005956739,0.0002698092,0.0001281505,0.5574444,0.01566988,0.01375358,0.01134927,0.3936518],"study_design_scores_gemma":[0.00003704129,0.0001141342,0.0002881937,0.00001788285,0.0000534907,0.00006791521,0.00001740598,0.9838626,0.005110356,0.009044906,0.001372101,0.00001403148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08234344,0.001766481,0.9021242,0.0004898452,0.0002254679,0.0002187714,0.0006019126,0.008246848,0.003983179],"genre_scores_gemma":[0.6319886,0.0006094612,0.3528821,0.0006032924,0.0001214362,0.0006342433,0.002619114,0.000765188,0.009776395],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004361763,"threshold_uncertainty_score":0.01459152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01055445237285489,"score_gpt":0.256521516027805,"score_spread":0.2459670636549502,"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."}}