{"id":"W2623263179","doi":"","title":"Testing the Equality of Learning Rates Using a Linear Hypothesis","year":2003,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Curvature; Mathematics; Function (biology); Power function; Scaling; Linear model; Statistical hypothesis testing; Noise (video); Power (physics); Test (biology); Applied mathematics; Statistics; Econometrics; Artificial intelligence; Computer science; Mathematical analysis","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":[0.1176368,0.00257208,0.003973328,0.003844019,0.002250524,0.00649726,0.006586576,0.006499003,0.01617089],"category_scores_gemma":[0.4560721,0.001260802,0.004755827,0.002626038,0.01225674,0.01309808,0.005461877,0.006602789,0.003939533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002421943,"about_ca_system_score_gemma":0.00338656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001314666,"about_ca_topic_score_gemma":0.0003386882,"domain_scores_codex":[0.8138283,0.1116407,0.01128825,0.03584775,0.02202615,0.005368811],"domain_scores_gemma":[0.2603409,0.6885141,0.01538715,0.02356889,0.009470518,0.002718489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0331923,0.00568827,0.3151402,0.003760966,0.01376874,0.003569527,0.007409492,0.05282665,0.01508963,0.2056306,0.00986304,0.3340605],"study_design_scores_gemma":[0.004279986,0.01642759,0.1113088,0.001048167,0.001717942,0.003551434,0.003194161,0.4014285,0.02178816,0.4223279,0.01224479,0.0006825965],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4125328,0.001255905,0.5545115,0.00396941,0.0007692181,0.001490314,0.001487536,0.000696555,0.02328684],"genre_scores_gemma":[0.9325923,0.0002752047,0.05975309,0.001661445,0.0005760696,0.00219434,0.001383784,0.0001512459,0.001412625],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1176368,"threshold_uncertainty_score":0.6221303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06398610123051654,"score_gpt":0.2561197025026501,"score_spread":0.1921336012721336,"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."}}