{"id":"W2124620066","doi":"10.1109/ijcnn.2000.859437","title":"Input-side training in constructive neural networks based on error scaling and pruning","year":2000,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Constructive; Pruning; Computer science; Generalization; Artificial neural network; Scaling; Feedforward neural network; Artificial intelligence; Algorithm; Feed forward; Piecewise; Machine learning; Mathematics; Process (computing); Engineering","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":[0.000122144,0.0001049954,0.0001190688,0.00005687276,0.000121214,0.000106637,0.0002119829,0.00004037961,0.0000279005],"category_scores_gemma":[0.000005024835,0.0000925148,0.00002283849,0.0003619947,0.00005580575,0.000192388,0.00003561216,0.0001913968,0.000002553358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001287773,"about_ca_system_score_gemma":0.00001871578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002557481,"about_ca_topic_score_gemma":0.00002617339,"domain_scores_codex":[0.9991374,0.00004119126,0.0001624691,0.000317944,0.00009087036,0.000250131],"domain_scores_gemma":[0.9995113,0.0001706642,0.00003046756,0.0002011825,0.00001146174,0.0000749055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006903414,0.00001239665,0.0006693745,0.000001279597,0.000001622497,0.000008963282,0.0003108479,0.4189231,0.00002663834,0.01294115,0.00003207094,0.5670657],"study_design_scores_gemma":[0.00024903,0.00002629699,0.003191258,0.0000242092,0.000001167484,0.00001028906,0.00005142426,0.9953691,0.00003348793,0.0007836746,0.0001474644,0.000112584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6273888,0.0000471665,0.351896,0.002423496,0.0001109598,0.0003243747,9.891201e-7,0.0002207743,0.01758747],"genre_scores_gemma":[0.9818586,0.000003358333,0.01639408,0.001615361,0.00005187737,0.00001608967,0.000001148132,0.000005878705,0.00005365124],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5764461,"threshold_uncertainty_score":0.3772644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02182585293641065,"score_gpt":0.2511428781424905,"score_spread":0.2293170252060798,"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."}}