{"id":"W2065005304","doi":"10.1016/j.neunet.2004.02.002","title":"New training strategies for constructive neural networks with application to regression problems","year":2004,"lang":"en","type":"article","venue":"Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Constructive; Computer science; Pruning; Artificial neural network; Feed forward; Generalization; Artificial intelligence; Feedforward neural network; Process (computing); Machine learning; Training (meteorology); Mathematics; Control engineering; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001316947,0.0003830141,0.0003451625,0.00007988314,0.0004533789,0.0004654964,0.0009035682,0.0001562485,0.000002907342],"category_scores_gemma":[0.000005662699,0.0002946942,0.000108277,0.0009753507,0.00008151994,0.0007782648,0.0001611532,0.0004033124,0.000002895735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006258675,"about_ca_system_score_gemma":0.0001080513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006358274,"about_ca_topic_score_gemma":0.000144412,"domain_scores_codex":[0.9976419,0.00003791955,0.0003917576,0.0008928078,0.0002634044,0.0007722357],"domain_scores_gemma":[0.9984098,0.0001471184,0.0002340635,0.0006757735,0.000143323,0.0003899053],"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":[0.00003816987,0.00001611659,0.00003770418,0.000004588275,0.00001018161,0.00000248043,0.0002461482,0.7805612,0.0001002827,0.0430994,0.0006811492,0.1752025],"study_design_scores_gemma":[0.0009366816,0.0004109828,0.000297361,0.00007285066,0.00001765725,0.00007441333,0.0001165792,0.9861653,0.00004392444,0.01007484,0.001374464,0.0004149816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008041153,0.0001878388,0.9857052,0.003314967,0.0003571685,0.001748277,0.000003197842,0.0004144742,0.0002277412],"genre_scores_gemma":[0.9232033,0.00001197469,0.07410809,0.001196117,0.0008707008,0.0004952872,0.00002813431,0.00004020589,0.00004622915],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9151621,"threshold_uncertainty_score":0.9999505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02026645845618289,"score_gpt":0.2586138086660905,"score_spread":0.2383473502099076,"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."}}