{"id":"W2758000438","doi":"10.1109/tnnls.2017.2748585","title":"A Novel Pruning Algorithm for Smoothing Feedforward Neural Networks Based on Group Lasso Method","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Specialized Research Fund for the Doctoral Program of Higher Education of China; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Shandong Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"MNIST database; Smoothing; Pruning; Artificial neural network; Generalization; Computer science; Algorithm; Backpropagation; Feedforward neural network; Mathematical optimization; Artificial intelligence; Mathematics; Machine learning","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":[0.001732245,0.0007382586,0.001231982,0.00093853,0.0005444522,0.0007243034,0.001448168,0.001340948,0.001507576],"category_scores_gemma":[0.003298709,0.00041862,0.0007635112,0.0008869446,0.0005845011,0.001312123,0.0008990027,0.001620976,0.0005197424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003540458,"about_ca_system_score_gemma":0.0008157989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001680042,"about_ca_topic_score_gemma":0.002386707,"domain_scores_codex":[0.9991853,0.0001898277,0.00006102946,0.0001079722,0.0003944428,0.00006148449],"domain_scores_gemma":[0.998887,0.0005105575,0.0001226436,0.0001328043,0.0003062409,0.00004067769],"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":[0.0002423222,0.000114913,0.001179254,0.0002355505,0.0001680976,0.0002426997,0.000172246,0.3878864,0.01954777,0.02604472,0.005396418,0.5587696],"study_design_scores_gemma":[0.00001860491,0.00003779289,0.000205679,0.00001367912,0.00001855937,0.00006120659,0.000007580776,0.9906703,0.002526684,0.004182462,0.002246461,0.00001088984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003728156,0.0001997309,0.9953321,0.00006289806,0.00003979245,0.00002342734,0.00001751973,0.000183527,0.0004128228],"genre_scores_gemma":[0.1341378,0.0005923701,0.8608245,0.000208384,0.0001538923,0.0002352419,0.0002038435,0.0001686583,0.003475434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001732245,"threshold_uncertainty_score":0.009161115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0211540683367614,"score_gpt":0.2588989068865793,"score_spread":0.237744838549818,"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."}}