{"id":"W2138382551","doi":"10.1109/mwscas.2011.6026515","title":"Performance analysis of table-based approximations of the hyperbolic tangent activation function","year":2011,"lang":"en","type":"article","venue":"","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"CMC Microsystems","keywords":"Activation function; Hyperbolic function; Artificial neural network; Computer science; Function approximation; Lookup table; Field-programmable gate array; Function (biology); Network topology; Algorithm; Preprocessor; Rprop; Artificial intelligence; Recurrent neural network; Mathematics; Computer hardware; Types of artificial neural networks","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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":[0.00004271875,0.00004647028,0.00009340716,0.00006981563,0.00004545029,0.000002216155,0.00005777811,0.00001433505,0.0012188],"category_scores_gemma":[7.859272e-7,0.00003034633,0.00009407032,0.0006298817,0.00002523491,0.00007099487,0.00000942444,0.0000387923,0.00000117064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004972346,"about_ca_system_score_gemma":0.00001765665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001302786,"about_ca_topic_score_gemma":0.000002118721,"domain_scores_codex":[0.9996279,0.00001710776,0.0001445558,0.0000698193,0.00008466423,0.00005595736],"domain_scores_gemma":[0.9996244,0.000008710202,0.0001265531,0.0001626636,0.00006338488,0.00001425906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001984191,0.00107064,0.5834415,0.00005147306,0.001654366,7.905507e-9,0.0008087892,0.2321915,0.03589056,0.06878331,0.0008010393,0.07510844],"study_design_scores_gemma":[0.0002189157,0.00003584838,0.2002547,0.00001082726,0.0004935119,1.878127e-8,0.0001597311,0.6345353,0.1638206,0.0001769682,0.000217611,0.00007591809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9060844,0.00000179879,0.07502525,0.00002386609,0.00005442481,0.00009030708,0.000004307011,0.000006755668,0.0187089],"genre_scores_gemma":[0.999338,6.16822e-7,0.0002649053,0.00001942585,0.00002293937,0.00001242796,0.00001583754,0.00000289262,0.0003229903],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4023438,"threshold_uncertainty_score":0.9996942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0331347210963138,"score_gpt":0.2100696817701974,"score_spread":0.1769349606738836,"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."}}