{"id":"W2593267444","doi":"","title":"An Empirical Analysis of Deep Network Loss Surfaces","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Maxima and minima; Dimension (graph theory); Computer science; Regular polygon; Mathematical optimization; Artificial neural network; Stochastic neural network; Convex optimization; Function (biology); Stochastic optimization; Mathematics; Artificial intelligence; Geometry; Recurrent neural network; Combinatorics; Mathematical analysis","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":[0.009493444,0.0009407977,0.0009391655,0.001724388,0.000687623,0.001781083,0.001365566,0.001835256,0.003051493],"category_scores_gemma":[0.07978334,0.0006046823,0.0005348506,0.001198363,0.003095712,0.004048074,0.00267121,0.003466249,0.0004247166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001711153,"about_ca_system_score_gemma":0.0007216546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001606763,"about_ca_topic_score_gemma":0.001223932,"domain_scores_codex":[0.9970207,0.001202527,0.000150018,0.0004582822,0.0009523131,0.0002161975],"domain_scores_gemma":[0.9501443,0.03863392,0.002341638,0.004259451,0.003718686,0.0009021321],"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":[0.0005847872,0.0002445445,0.03103826,0.000498826,0.0001413507,0.0003041537,0.0005061998,0.7617822,0.004840137,0.100719,0.01389872,0.0854418],"study_design_scores_gemma":[0.00004049945,0.0001782596,0.01253527,0.0001435358,0.0000227167,0.0003719809,0.0001976456,0.9206665,0.00348495,0.05958672,0.00272325,0.00004876313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6395591,0.005498798,0.3346801,0.004821735,0.0001642686,0.0001118656,0.001829488,0.001451762,0.01188276],"genre_scores_gemma":[0.9689376,0.0007120264,0.02700261,0.0001902566,0.00006722382,0.0001025491,0.001564654,0.000311435,0.001111648],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009493444,"threshold_uncertainty_score":0.05020672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07105419130914059,"score_gpt":0.247569314515302,"score_spread":0.1765151232061614,"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."}}