{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003230896,0.001865267,0.001223779,0.001527796,0.0007226181,0.001331142,0.002638057,0.00214416,0.004368614],"category_scores_gemma":[0.01491752,0.001060601,0.001042014,0.001341219,0.001411042,0.002251393,0.002373369,0.003013572,0.001412149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006295143,"about_ca_system_score_gemma":0.0006753011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001183482,"about_ca_topic_score_gemma":0.002536142,"domain_scores_codex":[0.9987549,0.0006752246,0.00007881661,0.0001092528,0.0003163058,0.0000655173],"domain_scores_gemma":[0.9949048,0.003648067,0.0002147246,0.0002817736,0.0008287588,0.0001219585],"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":[0.0001248897,0.0001531406,0.0005937215,0.0004101242,0.0001204763,0.0002378838,0.0003437989,0.4372477,0.009087437,0.210408,0.005978935,0.3352939],"study_design_scores_gemma":[0.00001391252,0.00002836502,0.00004925186,0.0000351013,0.00002143548,0.00006053353,0.00001504355,0.9615563,0.001511496,0.03458054,0.002116519,0.00001155399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001159453,0.0002691784,0.9968624,0.00007492409,0.00004365156,0.00002216761,0.000008320898,0.0001044095,0.001455529],"genre_scores_gemma":[0.08880808,0.0009449936,0.9037946,0.0002488242,0.0002675499,0.0003459943,0.00008646137,0.0004354954,0.005067974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004368614,"threshold_uncertainty_score":0.01708686,"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."}}