{"id":"W2142343760","doi":"10.1109/iscas.2009.5118213","title":"Efficient hardware implementation of the hyperbolic tangent sigmoid function","year":2009,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"CMC Microsystems","keywords":"Sigmoid function; Hyperbolic function; Activation function; Computer science; Tangent; Lookup table; Very-large-scale integration; Piecewise; Inverse trigonometric functions; Artificial neural network; Computer hardware; Mathematics; Embedded system; Artificial intelligence; Mathematical analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.00005106293,0.0000441905,0.00004248288,0.00001533528,0.00008456402,0.00002278927,0.0002624861,0.00001137845,0.00002937785],"category_scores_gemma":[0.000001009429,0.00002734625,0.00004127609,0.0002758582,0.000008497303,0.00003510687,0.00004604425,0.00003087851,0.000009285986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001178142,"about_ca_system_score_gemma":0.00001324821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001597693,"about_ca_topic_score_gemma":0.00000962612,"domain_scores_codex":[0.9995275,0.00001411821,0.0001134184,0.0001225895,0.0001324687,0.00008986601],"domain_scores_gemma":[0.9995984,0.000009550125,0.00005152625,0.0002848758,0.00003414153,0.00002150719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000002602051,0.0001236205,0.0007432762,0.000003340281,0.00000807478,2.083024e-7,0.0002749559,0.01195228,0.03785696,0.4451855,0.008391426,0.4954578],"study_design_scores_gemma":[0.000833905,0.0003952259,0.6180212,0.00002058594,0.00003517701,0.0000106896,0.0002855621,0.2202498,0.1074352,0.01115061,0.04118919,0.00037286],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4860394,0.00008500016,0.5012342,0.008991547,0.0002786457,0.00044118,0.000002087094,0.0001075708,0.002820334],"genre_scores_gemma":[0.9977476,0.000002678426,0.001232635,0.0008361307,0.00003561288,0.000008077509,8.035544e-7,0.000001318522,0.0001351241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.617278,"threshold_uncertainty_score":0.1115148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01164711269561237,"score_gpt":0.2543881834724698,"score_spread":0.2427410707768574,"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."}}