{"id":"W4386598466","doi":"10.1109/icip49359.2023.10222624","title":"Dodging the Double Descent in Deep Neural Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Grand Équipement National De Calcul Intensif; Canadian Institute for Advanced Research","keywords":"Regularization (linguistics); Phenomenon; Computer science; Gradient descent; Generalization; Perspective (graphical); Deep neural networks; Deep learning; Artificial neural network; Artificial intelligence; Stochastic gradient descent; Descent (aeronautics); Machine learning; Mathematical optimization; Mathematics; Epistemology; Engineering; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001556908,0.00007983497,0.0000669631,0.00005348015,0.0001509641,0.00008353384,0.000817782,0.00002286079,0.000006548857],"category_scores_gemma":[0.000004380289,0.00005395515,0.00002890269,0.001659057,0.00002735249,0.0002327269,0.0003765408,0.0001626725,0.00007970089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002638145,"about_ca_system_score_gemma":0.000005301398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001652593,"about_ca_topic_score_gemma":0.0001223161,"domain_scores_codex":[0.9991111,0.00002515277,0.0001447652,0.0002553368,0.0001195937,0.0003440638],"domain_scores_gemma":[0.9992519,0.0001497736,0.00003072049,0.0005078285,0.0000154055,0.00004434673],"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":[0.000002466211,0.000009859325,0.001145073,8.819126e-7,0.000001443677,0.000008220352,0.000121789,0.8469787,0.00004252364,0.08217311,0.0009215798,0.06859431],"study_design_scores_gemma":[0.0001456632,0.000004696817,0.00616635,0.000001916702,5.735951e-7,0.000004568964,0.00001698707,0.9894456,0.00005765221,0.002881882,0.00120286,0.00007121758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01193951,0.00007082184,0.9779637,0.007517025,0.0002233519,0.000273862,5.418546e-8,0.0005151682,0.001496542],"genre_scores_gemma":[0.9938664,0.00002814968,0.004754222,0.000929544,0.00007898709,0.00008469966,0.000001379286,0.000007296197,0.0002492732],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9819269,"threshold_uncertainty_score":0.2200227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02933795449060126,"score_gpt":0.2772926482744985,"score_spread":0.2479546937838972,"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."}}