{"id":"W2284875084","doi":"10.12943/anr.2013.00008","title":"Using Function Approximation to Determine Neural Network Accuracy","year":2013,"lang":"en","type":"article","venue":"AECL Nuclear Review","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Atomic Energy (Canada)","funders":"","keywords":"Artificial neural network; Computer science; Outlier; Function approximation; Activation function; Range (aeronautics); Algorithm; Artificial intelligence; Feedforward neural network; Probabilistic neural network; Function (biology); Time delay neural network; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.007209372,0.001210364,0.001466468,0.002323051,0.0004337349,0.001782461,0.001745407,0.002243566,0.001027041],"category_scores_gemma":[0.04063111,0.0006440759,0.0007241547,0.001232978,0.001071319,0.002845221,0.0009914204,0.002044323,0.0005720783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001681351,"about_ca_system_score_gemma":0.0008777379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006695068,"about_ca_topic_score_gemma":0.003674937,"domain_scores_codex":[0.9974827,0.0007599104,0.0002896713,0.0004351375,0.0008907124,0.0001419067],"domain_scores_gemma":[0.9834926,0.01136313,0.0009290325,0.001212026,0.002911671,0.00009150963],"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":[0.0001302348,0.00003273089,0.006417456,0.0003339527,0.0002348718,0.0000830071,0.0001595621,0.7759948,0.003768234,0.01507151,0.001262333,0.1965114],"study_design_scores_gemma":[0.000008328252,0.00003947132,0.001502152,0.0000799913,0.00002694378,0.00006043291,0.00002063465,0.9836473,0.00427144,0.009095496,0.001224386,0.0000234018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03143082,0.00455145,0.9587719,0.0004483378,0.0001731805,0.0000601746,0.0001205903,0.0009141886,0.003529332],"genre_scores_gemma":[0.5955011,0.005134394,0.3956959,0.0002612751,0.0001612124,0.0002478653,0.0004289026,0.0003163516,0.002252906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007209372,"threshold_uncertainty_score":0.0381273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05983260690616459,"score_gpt":0.2897313741670672,"score_spread":0.2298987672609026,"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."}}