{"id":"W4382986740","doi":"10.1017/apr.2023.3","title":"-Stable convergence of heavy-/light-tailed infinitely wide neural networks","year":2023,"lang":"en","type":"article","venue":"Advances in Applied Probability","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Mathematics; Independent and identically distributed random variables; Artificial neural network; Perceptron; Heavy-tailed distribution; Limit (mathematics); Distribution (mathematics); Stable distribution; Convergence (economics); Series (stratigraphy); Applied mathematics; Random variable; Statistical physics; Artificial intelligence; Mathematical analysis; Statistics; Computer science; Physics","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":[0.0005199551,0.0001878072,0.0003144955,0.00007832627,0.0001055111,0.00003624865,0.0009562289,0.00007506159,0.00001644407],"category_scores_gemma":[0.00004439515,0.000173129,0.00006334769,0.002196619,0.000147413,0.0004235374,0.0003766348,0.0002482892,0.00002683539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003935609,"about_ca_system_score_gemma":0.00003389555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001138995,"about_ca_topic_score_gemma":0.00008267692,"domain_scores_codex":[0.9980224,0.00005900397,0.0005543042,0.0006378763,0.0002411198,0.0004853273],"domain_scores_gemma":[0.998309,0.0004629289,0.0001835053,0.0008956477,0.00005752172,0.00009142814],"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":[0.00008322615,0.0001795768,0.02937065,0.0001166714,0.000007346906,0.000004681619,0.0001995161,0.6024837,0.0005005672,0.2973137,0.0004974219,0.06924293],"study_design_scores_gemma":[0.0005303609,0.00008483429,0.01124739,0.00003074549,0.000005062009,0.000001918631,0.00002744,0.7219095,0.002996892,0.2450463,0.01769144,0.0004280497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.426299,0.002108216,0.5413678,0.003693114,0.001587242,0.00396237,0.00001849865,0.001612838,0.019351],"genre_scores_gemma":[0.9887933,0.0002669136,0.01034963,0.0001939866,0.00003891044,0.0003087054,0.000007475919,0.00001024053,0.00003081754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5624943,"threshold_uncertainty_score":0.7059997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01662740427759366,"score_gpt":0.2582175846380347,"score_spread":0.241590180360441,"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."}}