{"id":"W2997330246","doi":"10.48550/arxiv.1912.11511","title":"An Analysis of the Expressiveness of Deep Neural Network Architectures Based on Their Lipschitz Constants","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Lipschitz continuity; Computer science; Range (aeronautics); Constant (computer programming); Artificial neural network; Function (biology); Activation function; Nonlinear system; Deep neural networks; Power (physics); Artificial intelligence; Mathematics; Pure 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014164,0.0002414604,0.0004665891,0.0002111245,0.000117417,0.00003691079,0.002716322,0.0001384089,0.00001283651],"category_scores_gemma":[0.000007480066,0.0001827289,0.0004466313,0.001537547,0.0001842097,0.00005753677,0.000783485,0.0003783807,9.551212e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002801215,"about_ca_system_score_gemma":0.00007831429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000583652,"about_ca_topic_score_gemma":0.00007511595,"domain_scores_codex":[0.9983982,0.0003028671,0.0002268586,0.000716613,0.0001168512,0.00023857],"domain_scores_gemma":[0.9966112,0.0003292873,0.0005386106,0.002321132,0.0001191225,0.00008069792],"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":[0.00003002641,0.00008172449,0.02242926,0.00001852268,0.0001467701,0.000003435185,0.00005973034,0.9623789,0.0001076489,0.01405607,0.000008279381,0.0006796424],"study_design_scores_gemma":[0.0001552544,0.00004044865,0.04161944,0.00005554967,0.0002155101,2.292028e-7,0.00001612161,0.9537541,0.0004634255,0.003495906,0.00001196676,0.0001720155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6423251,0.00002158776,0.3568538,0.00004452544,0.0001752233,0.0002522299,0.00004114896,0.00003406067,0.0002523398],"genre_scores_gemma":[0.9993993,0.000007521359,0.0003747215,0.0001365824,0.00003828389,0.000001334192,0.00001267775,0.000009621131,0.00001996682],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3570742,"threshold_uncertainty_score":0.7451469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03538048507252838,"score_gpt":0.1912537584626319,"score_spread":0.1558732733901035,"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."}}