{"id":"W2188755879","doi":"","title":"FOURIER NEURAL NETWORKS: AN APPROACH WITH SINUSOIDAL ACTIVATION FUNCTIONS 1","year":2003,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial neural network; Perceptron; Activation function; Connection (principal bundle); Computer science; Fourier series; Fourier transform; Biological system; Algorithm; Topology (electrical circuits); Mathematics; Artificial intelligence; Mathematical analysis; Geometry; Combinatorics; Biology","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":[0.00008561178,0.000112449,0.00007772882,0.00003535609,0.0002596636,0.0001883149,0.0002703905,0.00003969499,0.0000242894],"category_scores_gemma":[0.000003492911,0.00008138069,0.0000265548,0.0005636605,0.00003071965,0.0007884709,0.00002808593,0.0001295854,0.000007440898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001397042,"about_ca_system_score_gemma":0.00002096679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001108002,"about_ca_topic_score_gemma":0.000007328074,"domain_scores_codex":[0.9991221,0.00005070122,0.0001090135,0.0003435789,0.0001445745,0.0002299735],"domain_scores_gemma":[0.9992562,0.00003228045,0.00004453029,0.0005010272,0.00005495723,0.0001109906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001054724,0.0003685356,0.001228876,0.000002961341,0.0000198179,0.000001854162,0.00009763284,0.4248212,0.0002157311,0.5242593,0.005519984,0.04345354],"study_design_scores_gemma":[0.0001765709,0.00007865154,0.001103451,0.000001728543,0.000003852026,0.00003004258,0.00003833085,0.9931497,0.0001237133,0.0005567262,0.004577365,0.0001598492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02127646,0.000006313372,0.9635498,0.0003807576,0.00005770444,0.0001724711,2.577702e-7,0.0002160078,0.01434022],"genre_scores_gemma":[0.9167595,7.056765e-7,0.08128191,0.0005749578,0.0001047579,0.00006209155,0.000008932667,0.000009133474,0.001198013],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.895483,"threshold_uncertainty_score":0.3318608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01683285455215492,"score_gpt":0.2169953947961231,"score_spread":0.2001625402439682,"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."}}