{"id":"W2191671953","doi":"10.1016/j.chemolab.2015.10.005","title":"Efficient variable selection batch pruning algorithm for artificial neural networks","year":2015,"lang":"en","type":"article","venue":"Chemometrics and Intelligent Laboratory Systems","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"","keywords":"Pruning; Artificial neural network; Computer science; Artificial intelligence; Selection (genetic algorithm); Variable (mathematics); Feature selection; Machine learning; Algorithm; Pattern recognition (psychology); Mathematics; Biology","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":[0.003118603,0.0008391724,0.001569527,0.001131671,0.0008265986,0.0009799327,0.002917521,0.00130334,0.003275745],"category_scores_gemma":[0.006474924,0.0006830882,0.0006934878,0.001245071,0.0005262734,0.0009330773,0.0009535209,0.001917196,0.0009268996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007947732,"about_ca_system_score_gemma":0.002372378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008963609,"about_ca_topic_score_gemma":0.01378252,"domain_scores_codex":[0.9988661,0.0003787095,0.0001066287,0.0001467724,0.0003928091,0.00010902],"domain_scores_gemma":[0.9970499,0.001578871,0.0001473122,0.0002745601,0.0008860593,0.00006332457],"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":[0.0005930573,0.0002677816,0.001928998,0.0001753229,0.000179433,0.0001947846,0.00009579257,0.2517304,0.008086777,0.009190314,0.01363672,0.7139205],"study_design_scores_gemma":[0.00006242383,0.00004699424,0.0005490325,0.00001473904,0.00003655798,0.0000502196,0.000007767242,0.9921962,0.002847955,0.002859326,0.001320988,0.000007827191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02342546,0.0008900434,0.9720133,0.0002663548,0.0001713727,0.0001351969,0.0001954855,0.001381774,0.001520911],"genre_scores_gemma":[0.165739,0.0003593047,0.8251411,0.0002847789,0.0001904257,0.0004374409,0.000989555,0.0002703106,0.006588062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008963609,"threshold_uncertainty_score":0.01782286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04604538526193617,"score_gpt":0.2907700699489588,"score_spread":0.2447246846870227,"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."}}