{"id":"W3212638064","doi":"10.48550/arxiv.2012.12896","title":"How Does a Neural Network's Architecture Impact Its Robustness to Noisy Labels?","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Robustness (evolution); Computer science; Network architecture; Architecture; Artificial intelligence; Predictive power; Artificial neural network; Machine learning; Pattern recognition (psychology)","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":[0.0001051085,0.0001808041,0.0001662375,0.00007819163,0.000172227,0.0002544648,0.001141689,0.00006359327,0.00001952685],"category_scores_gemma":[0.00009628879,0.0001459792,0.00009042193,0.00122196,0.00002496624,0.0005796275,0.0003950025,0.0002807615,0.00005331505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004204281,"about_ca_system_score_gemma":0.00004319156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002752041,"about_ca_topic_score_gemma":0.00003292139,"domain_scores_codex":[0.9986788,0.0001416721,0.00008108471,0.0006634383,0.00008365125,0.0003513703],"domain_scores_gemma":[0.9988914,0.00007075919,0.00008386994,0.0005269715,0.0000716368,0.000355394],"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":[0.00004203392,0.00001977909,0.004811266,0.00001463048,0.00002059375,0.00008690041,0.0002532138,0.9696892,0.0003152835,0.01869774,0.001154549,0.004894846],"study_design_scores_gemma":[0.0002955288,0.0001390263,0.007777532,0.000009772003,0.00001370056,0.00000513128,0.00003303235,0.9858606,0.00005639447,0.0003188057,0.005243576,0.0002469154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2935058,0.00001803074,0.695531,0.01017096,0.000125358,0.0001325808,0.000008739442,0.0002690165,0.0002384851],"genre_scores_gemma":[0.9961846,0.000006684898,0.002080047,0.0007549013,0.0001904023,4.503065e-7,0.00001259738,0.00001071462,0.0007595335],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7026789,"threshold_uncertainty_score":0.595286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05291688621403645,"score_gpt":0.1930089042461076,"score_spread":0.1400920180320711,"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."}}