{"id":"W2111377264","doi":"10.1109/icnn.1996.548874","title":"An adaptive and fully sparse training approach for multilayer perceptrons","year":2002,"lang":"en","type":"article","venue":"Proceedings of International Conference on Neural Networks (ICNN'96)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Backpropagation; Computer science; Artificial neural network; Artificial intelligence; Feed forward; Perceptron; Process (computing); Sparse approximation; Training (meteorology); Multilayer perceptron; Set (abstract data type); Pattern recognition (psychology); Feedforward neural network; Machine learning; Engineering; Control 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001934361,0.0002989243,0.00030084,0.0001406662,0.000207672,0.0003577638,0.001161138,0.0001165101,0.0000468082],"category_scores_gemma":[0.00002732822,0.0002732136,0.000109758,0.0002365269,0.0001456125,0.000941691,0.0001618798,0.0003315241,0.000002419085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003293212,"about_ca_system_score_gemma":0.00001241293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007547203,"about_ca_topic_score_gemma":0.000002390337,"domain_scores_codex":[0.9980329,0.0000116853,0.0004096776,0.000767129,0.0003545003,0.0004241125],"domain_scores_gemma":[0.9986542,0.00009718409,0.0002898234,0.0001769986,0.000576018,0.0002057058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002171568,0.0005693162,0.001015938,0.0000320918,0.00009854849,0.000002365588,0.002311814,0.01898232,0.006429431,0.8202345,0.00423407,0.1458725],"study_design_scores_gemma":[0.0004901672,0.0004902548,0.0007152246,0.00004034988,0.00001255692,0.00002496807,0.0003962382,0.9955651,0.0002034154,0.001414756,0.0003634615,0.000283462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4338864,0.0002624383,0.5180789,0.01052492,0.0009344237,0.002554297,0.00008363901,0.0006235724,0.03305139],"genre_scores_gemma":[0.9615588,0.0001185509,0.03699042,0.0004700955,0.0003964849,0.0001887236,0.00001330219,0.00002324039,0.0002404095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9765828,"threshold_uncertainty_score":0.999972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1040852294187849,"score_gpt":0.2857363058533977,"score_spread":0.1816510764346128,"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."}}