{"id":"W3174935984","doi":"","title":"Size and Depth Separation in Approximating Natural Functions with Neural Networks","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Lipschitz continuity; Bounded function; Mathematics; Function (biology); Polynomial; Artificial neural network; Constant (computer programming); Computational complexity theory; Discrete mathematics; Algorithm; Computer science; Pure mathematics; Artificial intelligence; 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":[0.002249872,0.001300104,0.0009038605,0.0008891154,0.0007273795,0.002020515,0.002046663,0.001663028,0.003546507],"category_scores_gemma":[0.01962749,0.000798873,0.001455312,0.000688157,0.002534882,0.009179484,0.003690764,0.003530227,0.0005604406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003639001,"about_ca_system_score_gemma":0.001513928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004462123,"about_ca_topic_score_gemma":0.00626872,"domain_scores_codex":[0.9981706,0.000566676,0.0001045806,0.0004168603,0.0005097059,0.0002315154],"domain_scores_gemma":[0.9911142,0.00670441,0.0004523427,0.001048602,0.000410522,0.0002697904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001050649,0.000157652,0.006625864,0.0005000503,0.000123872,0.0002587798,0.000799568,0.5878466,0.01403047,0.2672983,0.003983139,0.1173251],"study_design_scores_gemma":[0.00002284693,0.00007575023,0.0004273724,0.00003908793,0.00002902606,0.00007999965,0.00005514075,0.858995,0.003753682,0.1343496,0.002156436,0.00001601969],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1834853,0.001693191,0.79198,0.003640998,0.0000968615,0.0001153199,0.0004273904,0.001917666,0.01664326],"genre_scores_gemma":[0.7567539,0.0009423294,0.2338996,0.0007982903,0.0001149842,0.0001844053,0.0005477031,0.0004031052,0.006355707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004462123,"threshold_uncertainty_score":0.02640289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01089248834608676,"score_gpt":0.2541372997461577,"score_spread":0.243244811400071,"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."}}