{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001315108,0.0001160979,0.00017407,0.00002091915,0.0001747779,0.0001673245,0.0004340065,0.00002633645,0.000181608],"category_scores_gemma":[0.00002524956,0.00009784955,0.00006994549,0.0005684947,0.00001052162,0.0006505091,0.0001988907,0.00009157175,0.001030592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001968429,"about_ca_system_score_gemma":0.000006915392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002060833,"about_ca_topic_score_gemma":9.415172e-7,"domain_scores_codex":[0.9990377,0.00005342233,0.0002586456,0.0002812826,0.0001315575,0.0002374284],"domain_scores_gemma":[0.9991429,0.00004227405,0.00011449,0.0005230457,0.00006547905,0.0001117437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.764226e-7,0.00002053452,0.00001798673,0.0001598867,0.000005528625,8.349379e-7,0.00001656328,0.001383983,0.0006432149,0.01437101,0.05600779,0.9273718],"study_design_scores_gemma":[0.00008956464,0.00006987052,0.001328799,0.0007608155,0.00003076822,0.00003984686,0.000001801165,0.5860661,0.00000908122,0.002401232,0.4089095,0.0002925495],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06331416,0.03547694,0.8440254,0.04168991,0.001697192,0.007649117,0.000002032839,0.001385527,0.004759717],"genre_scores_gemma":[0.538998,0.01011206,0.359985,0.08850135,0.001512988,0.0003870904,0.00001705074,0.0001149704,0.0003714917],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9270793,"threshold_uncertainty_score":0.9997472,"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."}}