{"id":"W3015482436","doi":"10.1016/j.neunet.2020.04.001","title":"A tight upper bound on the generalization error of feedforward neural networks","year":2020,"lang":"en","type":"article","venue":"Neural Networks","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ericsson (Canada)","funders":"","keywords":"Differentiable function; Generalization; Upper and lower bounds; Term (time); Artificial neural network; Feed forward; Feedforward neural network; Mathematics; Sensitivity (control systems); Computer science; Function (biology); Generalization error; Space (punctuation); Algorithm; Applied mathematics; Artificial intelligence; Mathematical analysis; Physics","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":[0.01164687,0.003891215,0.003433704,0.002356558,0.001631321,0.003732114,0.005271981,0.005847335,0.008621227],"category_scores_gemma":[0.06175458,0.001575239,0.001896271,0.0020782,0.003714462,0.008617307,0.007966233,0.01046359,0.003145233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002965684,"about_ca_system_score_gemma":0.002613856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003637418,"about_ca_topic_score_gemma":0.004749498,"domain_scores_codex":[0.9929239,0.001824966,0.0004161875,0.001304705,0.002549847,0.0009804423],"domain_scores_gemma":[0.9633911,0.02804749,0.0009462262,0.003502129,0.003441155,0.000671911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007621442,0.0002858241,0.001888723,0.001114112,0.0003620997,0.0004516151,0.0003318523,0.5653368,0.01058979,0.1923234,0.02418647,0.2023671],"study_design_scores_gemma":[0.00002376246,0.00007787541,0.0004936144,0.0002025081,0.00005215813,0.0001436507,0.00004212541,0.8772913,0.002683009,0.1160444,0.002915504,0.00003015073],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01951962,0.01185745,0.9434561,0.005606724,0.00114409,0.0001103262,0.0004941525,0.001686469,0.01612504],"genre_scores_gemma":[0.5644801,0.01232199,0.3728684,0.006017936,0.003014013,0.0007996224,0.001782472,0.002305546,0.03640999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01164687,"threshold_uncertainty_score":0.06159526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02096427600500496,"score_gpt":0.2424646085636059,"score_spread":0.2215003325586009,"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."}}