{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003475051,0.001243222,0.001043365,0.0008901725,0.0004400786,0.0007912947,0.002158789,0.001214976,0.001141625],"category_scores_gemma":[0.01389701,0.0005737629,0.0005985321,0.0007410655,0.001890871,0.002031636,0.00175569,0.001350071,0.0003845312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004452239,"about_ca_system_score_gemma":0.0005620926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005992045,"about_ca_topic_score_gemma":0.001034421,"domain_scores_codex":[0.9977269,0.0009873407,0.0001324977,0.0002126341,0.0008190878,0.0001215455],"domain_scores_gemma":[0.9935789,0.004180363,0.0005056782,0.0007456533,0.0008778078,0.0001116114],"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":[0.0002776139,0.0001239365,0.001499107,0.000277783,0.0001103584,0.0003920948,0.0003469272,0.523628,0.03147397,0.07072721,0.001089477,0.3700536],"study_design_scores_gemma":[0.0000178507,0.0001179285,0.0002465713,0.0000366135,0.00002872459,0.0002013927,0.00001692249,0.9660496,0.01606483,0.0159372,0.001262969,0.0000194648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01126062,0.0001456152,0.9868901,0.00005182537,0.00002655094,0.00003105055,0.000006796687,0.0002034434,0.001384106],"genre_scores_gemma":[0.3341513,0.0002913515,0.6634015,0.0001677889,0.00009296323,0.0001812588,0.00005586442,0.0001604211,0.001497627],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003475051,"threshold_uncertainty_score":0.01837808,"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."}}