{"id":"W2000956074","doi":"10.1109/tvlsi.2012.2232321","title":"Efficient VLSI Implementation of Neural Networks With Hyperbolic Tangent Activation Function","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Hyperbolic function; Activation function; Sigmoid function; Artificial neural network; Very-large-scale integration; Tangent; Nonlinear system; Computer science; Adder; Function (biology); Transfer function; Function approximation; Inverse trigonometric functions; Algorithm; Mathematics; Topology (electrical circuits); Mathematical analysis; Artificial intelligence; Engineering; Telecommunications","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004001316,0.0002975537,0.0003138626,0.0002498987,0.000419894,0.0001882422,0.0003379679,0.0001327262,0.00002764134],"category_scores_gemma":[0.000002330854,0.0002440493,0.0001447455,0.0009095986,0.00004785878,0.0004212606,0.000004619331,0.0003052888,0.00001871034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001419508,"about_ca_system_score_gemma":0.00004136428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001889441,"about_ca_topic_score_gemma":0.0003197594,"domain_scores_codex":[0.997632,0.0002354123,0.0006400481,0.0005653971,0.0005469699,0.0003801399],"domain_scores_gemma":[0.9984094,0.0001358328,0.0003725067,0.0006448627,0.0003069752,0.0001304248],"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":[0.00008143992,0.0003016111,0.00007518414,0.00002954727,0.00004733856,3.782001e-7,0.0003860986,0.9444061,0.005163615,0.003601542,0.000250295,0.04565684],"study_design_scores_gemma":[0.0007968833,0.0005431972,0.0009688488,0.00008913482,0.00005446231,0.00001120029,0.0005163764,0.9823036,0.01380553,0.00002339476,0.0006269031,0.0002604209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1613812,0.00002323783,0.8361398,0.0002539535,0.00109484,0.0007674756,0.00001940387,0.0001919128,0.0001282212],"genre_scores_gemma":[0.9981862,0.00001040341,0.0008732773,0.0001729487,0.0002076577,0.0003643768,0.00003363548,0.00002851216,0.0001229359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8368051,"threshold_uncertainty_score":0.995204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009279577385021536,"score_gpt":0.2313607662454921,"score_spread":0.2220811888604706,"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."}}