{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003296058,0.001047589,0.0007607282,0.0008812917,0.0005853581,0.002295431,0.001938533,0.001555488,0.002660912],"category_scores_gemma":[0.02428205,0.0009110793,0.001140537,0.0005365627,0.002785443,0.006963347,0.002841119,0.004034069,0.0003008105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00217109,"about_ca_system_score_gemma":0.0007955138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001026078,"about_ca_topic_score_gemma":0.0008247151,"domain_scores_codex":[0.9984735,0.0004193891,0.000109744,0.0003367029,0.0005106901,0.000149928],"domain_scores_gemma":[0.9839585,0.01275833,0.001103973,0.00116401,0.0005591427,0.0004560555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002243755,0.00005366092,0.001953605,0.0003313688,0.00007572203,0.0003537651,0.0004170359,0.4361395,0.01368478,0.5199037,0.000946182,0.02591635],"study_design_scores_gemma":[0.00001314545,0.00005970623,0.0003813985,0.00006837361,0.00002652426,0.0001481753,0.00003455766,0.7392197,0.002647584,0.2563613,0.001017862,0.00002152926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1650388,0.00204288,0.8122525,0.002267837,0.00006944052,0.0000597752,0.0003825825,0.0004692759,0.017417],"genre_scores_gemma":[0.9251398,0.001897904,0.06697344,0.0004704712,0.0001258214,0.0001760445,0.0002808979,0.0002611828,0.004674323],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003296058,"threshold_uncertainty_score":0.01743144,"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."}}