{"id":"W1577979322","doi":"10.1109/ijcnn.2001.939537","title":"Input decay: simple and effective soft variable selection","year":2002,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Overfitting; Regularization (linguistics); Computer science; Variable (mathematics); Simple (philosophy); Task (project management); Selection (genetic algorithm); Feature selection; Artificial intelligence; Machine learning; Mathematical optimization; Mathematics; Artificial neural network; 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":[0.007178741,0.001893724,0.002071192,0.001718865,0.0006729173,0.001738627,0.003069955,0.002504686,0.003207359],"category_scores_gemma":[0.01754672,0.0007271029,0.001440179,0.00159642,0.001437451,0.002267857,0.00395217,0.002857122,0.00159126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005229698,"about_ca_system_score_gemma":0.001489539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007291728,"about_ca_topic_score_gemma":0.001032653,"domain_scores_codex":[0.9961221,0.001774172,0.0002437767,0.0004478641,0.001144324,0.000267673],"domain_scores_gemma":[0.9937118,0.00275228,0.000394849,0.001384594,0.001496832,0.0002596018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007101751,0.0003963633,0.003239888,0.0003410858,0.0003303727,0.0003000968,0.0002174866,0.1561628,0.0194215,0.03366749,0.008385743,0.776827],"study_design_scores_gemma":[0.00009346989,0.000149763,0.0005456472,0.00004009362,0.00004834009,0.000116864,0.00002185623,0.9657023,0.007702692,0.02313451,0.002410163,0.00003423814],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007469582,0.000146772,0.9902855,0.0001209102,0.00005446431,0.00008245147,0.00005114927,0.001080407,0.0007087952],"genre_scores_gemma":[0.2820392,0.000330211,0.7100908,0.0006409634,0.0002642556,0.0006076784,0.0006658809,0.0006907933,0.004670236],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007178741,"threshold_uncertainty_score":0.03796524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009226466990641504,"score_gpt":0.2185175931543817,"score_spread":0.2092911261637402,"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."}}