{"id":"W2963746765","doi":"","title":"Training Neural Networks with Stochastic Hessian-Free Optimization","year":2013,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Overfitting; Hessian matrix; Autoencoder; Stochastic gradient descent; Computer science; Artificial intelligence; Stochastic optimization; Pattern recognition (psychology); Conjugate gradient method; Mathematical optimization; Dropout (neural networks); Artificial neural network; Machine learning; Algorithm; Mathematics; Applied mathematics","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":[0.001524479,0.001314376,0.001128535,0.0004498411,0.0003625821,0.0006858116,0.001334542,0.001500346,0.001892101],"category_scores_gemma":[0.004462682,0.001016761,0.00068087,0.0006033157,0.0008127487,0.001401676,0.001149788,0.001875019,0.0006701349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001108715,"about_ca_system_score_gemma":0.001369081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007417246,"about_ca_topic_score_gemma":0.01267303,"domain_scores_codex":[0.999403,0.000210624,0.00004149984,0.0001377724,0.0001449614,0.0000621594],"domain_scores_gemma":[0.9987215,0.0007477178,0.0001028462,0.0001615812,0.0002178177,0.00004834556],"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":[0.00006363618,0.0000552868,0.0004356622,0.00004553132,0.00005266993,0.00003355986,0.00002711024,0.9428384,0.002217313,0.005937986,0.001736233,0.04655648],"study_design_scores_gemma":[0.000003499038,0.000007552042,0.00002303301,0.000001168778,9.53718e-7,0.000001927182,7.273669e-7,0.998702,0.0002819464,0.0009154789,0.00006025238,0.000001444328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04563606,0.0003640542,0.9487727,0.0003181643,0.00005858634,0.00006565309,0.0001535259,0.002359147,0.002272092],"genre_scores_gemma":[0.6131285,0.0002170369,0.3794059,0.0003657876,0.00009400902,0.0002655666,0.0009225595,0.0004077379,0.005192744],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007417246,"threshold_uncertainty_score":0.0147481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0208903185049786,"score_gpt":0.2341014358258329,"score_spread":0.2132111173208543,"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."}}