{"id":"W2596625124","doi":"","title":"Nearly-tight VC-dimension bounds for piecewise linear neural networks","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"","keywords":"Dimension (graph theory); Upper and lower bounds; Piecewise linear function; Mathematics; Combinatorics; Omega; Piecewise; VC dimension; Function (biology); Range (aeronautics); Artificial neural network; Discrete mathematics; Mathematical analysis; Physics; Computer science","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":[0.0001813001,0.0001783839,0.0001772191,0.0001243156,0.0008498697,0.0002551481,0.001543113,0.0001157863,0.00001007241],"category_scores_gemma":[0.00009214447,0.0001939717,0.0001218783,0.0002236338,0.0001544526,0.00103009,0.0004834181,0.0001340228,0.00001279572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006659669,"about_ca_system_score_gemma":0.00003609918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003423592,"about_ca_topic_score_gemma":0.000008474907,"domain_scores_codex":[0.9987994,0.00003246304,0.0001387251,0.0006020685,0.00006690282,0.0003603868],"domain_scores_gemma":[0.9980704,0.00009710233,0.0002185809,0.001262048,0.0001945696,0.0001573526],"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":[0.00008181243,0.0001229411,0.003363823,0.00001463848,0.00004554944,0.0001022766,0.0001612596,0.3793272,0.00007724849,0.6112493,0.002362015,0.003091956],"study_design_scores_gemma":[0.0005854048,0.0001429131,0.0007297173,0.00001467289,0.00002047916,0.0000045777,0.00000573312,0.9901335,0.0002104548,0.007505646,0.0004248231,0.0002220599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02722023,0.00001841557,0.9706259,0.0002163787,0.000558419,0.0003144592,0.00000272617,0.0003740714,0.0006693476],"genre_scores_gemma":[0.9717298,0.00001470266,0.02689862,0.0001435604,0.00008850531,0.000001938269,0.000005224355,0.00001564447,0.001102011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9445096,"threshold_uncertainty_score":0.7909939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06326245405350339,"score_gpt":0.2035452813463818,"score_spread":0.1402828272928784,"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."}}