{"id":"W2160305096","doi":"10.1109/mwscas.1998.759553","title":"An algorithm for in-the-loop training based on activation function derivative approximation","year":2002,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Backpropagation; Very-large-scale integration; Artificial neural network; Computer science; Algorithm; Activation function; Obstacle; Loop (graph theory); Artificial intelligence; Mathematics","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":[0.0006066337,0.0007155113,0.0007108625,0.0004513715,0.0005066509,0.0005720246,0.001437481,0.001134906,0.003248109],"category_scores_gemma":[0.00164447,0.0003126805,0.0002942807,0.0004474043,0.0005853689,0.0009382564,0.0006196027,0.001442762,0.001280619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005586282,"about_ca_system_score_gemma":0.0007882629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001849449,"about_ca_topic_score_gemma":0.001837148,"domain_scores_codex":[0.9996631,0.00006155774,0.00002020414,0.00006785747,0.0001536872,0.00003352305],"domain_scores_gemma":[0.9996403,0.0001352669,0.00003208437,0.0000483316,0.0001257024,0.0000183274],"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":[0.000229356,0.0001148613,0.0005475466,0.0001498525,0.00006029984,0.0001102728,0.0001557715,0.3437096,0.02708272,0.0292501,0.003885137,0.5947044],"study_design_scores_gemma":[0.00002403231,0.00004366214,0.00009676527,0.000008260563,0.00001119782,0.00007864898,0.000006753639,0.9860844,0.007070235,0.003224511,0.003341941,0.00000957514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00119714,0.00003762795,0.9978973,0.00002909274,0.00002855796,0.00002111232,0.000004233083,0.0003331905,0.0004517262],"genre_scores_gemma":[0.09221658,0.0001145072,0.9045902,0.00008725031,0.00004260676,0.0001694994,0.00004000863,0.0001362717,0.002603048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003248109,"threshold_uncertainty_score":0.01086599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06076098240478691,"score_gpt":0.2688550982387101,"score_spread":0.2080941158339232,"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."}}