{"id":"W2099759795","doi":"10.1109/tnn.2005.851786","title":"Constructive Feedforward Neural Networks Using Hermite Polynomial Activation Functions","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Activation function; Constructive; Sigmoid function; Hermite polynomials; Artificial neural network; Computer science; Feedforward neural network; Orthonormal basis; Polynomial; Adaptation (eye); Function (biology); Constructive proof; Topology (electrical circuits); Mathematics; Artificial intelligence; Discrete mathematics; Pure mathematics; Combinatorics; Mathematical analysis","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001511622,0.0005326821,0.0004084379,0.0002546094,0.001256105,0.0003958626,0.0007812773,0.0003037769,0.00007557874],"category_scores_gemma":[0.000002908644,0.0005293587,0.0003719055,0.001434984,0.0002038437,0.001581856,0.00001738696,0.001201396,0.00002690173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002313463,"about_ca_system_score_gemma":0.00004650857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005607261,"about_ca_topic_score_gemma":0.000060916,"domain_scores_codex":[0.9969271,0.0001738013,0.0006470314,0.0009599675,0.0003853669,0.0009067212],"domain_scores_gemma":[0.998022,0.0003103583,0.00027745,0.0008876111,0.000154517,0.0003481009],"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":[0.00005257635,0.0001082486,0.00001764261,0.000001849482,0.00004060083,0.000003130619,0.0000331164,0.8031057,0.0002888427,0.000156063,0.0009025375,0.1952897],"study_design_scores_gemma":[0.0006699191,0.0001300499,0.0001986904,0.00002367064,0.00005652782,0.0001234962,0.00002326582,0.9960267,0.000800301,0.0000258985,0.001400068,0.0005214475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05255677,0.00007288246,0.9414409,0.001705516,0.00276314,0.0006136409,0.00001401587,0.0005873379,0.0002457302],"genre_scores_gemma":[0.9912047,0.00003684365,0.004665322,0.001727827,0.00182702,0.000110912,0.00001104681,0.000058994,0.0003572704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.938648,"threshold_uncertainty_score":0.9997158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01768520251766669,"score_gpt":0.2410274838492189,"score_spread":0.2233422813315522,"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."}}