{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001228926,0.0001105516,0.0002256724,0.0001058071,0.0004439563,0.00006719724,0.002121005,0.00005687468,0.00001742969],"category_scores_gemma":[0.000014863,0.0001192849,0.0001252007,0.001210074,0.0001934491,0.0008417008,0.0003401602,0.00009482136,0.00001710279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003009657,"about_ca_system_score_gemma":0.00001889736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003195691,"about_ca_topic_score_gemma":0.0002372285,"domain_scores_codex":[0.9989854,0.0000602592,0.0001252044,0.0005176047,0.00006313971,0.0002484557],"domain_scores_gemma":[0.9975464,0.0001057554,0.0002496351,0.001867396,0.00009439552,0.0001364289],"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":[0.000006760708,0.00004243016,0.1802762,0.000001156523,0.0000966912,0.00002514806,0.00004097956,0.7437633,0.000030979,0.07484379,0.00003708984,0.0008354794],"study_design_scores_gemma":[0.0001076487,0.00002733442,0.1667772,0.000001868546,0.0001199604,5.856435e-7,0.000008364005,0.8217131,0.00005506809,0.01085354,0.0002181826,0.0001171272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4433513,0.00001094777,0.5558857,0.00007969149,0.00004016609,0.0000466453,0.000001616649,0.000055009,0.0005289488],"genre_scores_gemma":[0.9929813,0.00003460425,0.006756738,0.00006234767,0.00003297785,2.827571e-7,0.000003421469,0.000005094226,0.000123199],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.54963,"threshold_uncertainty_score":0.4864296,"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."}}