{"id":"W4319339631","doi":"10.36227/techrxiv.22006742.v1","title":"Improving Image Recognition Accuracy in Neural Networks Using Fractional Natural Gradient Descent","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Science and Higher Education of the Russian Federation; Russian Science Foundation; Centre de Recherches Mathématiques","keywords":"MNIST database; Convexity; Gradient descent; Mathematics; Curvature; Rate of convergence; Convergence (economics); Artificial neural network; Momentum (technical analysis); Image (mathematics); Order (exchange); Applied mathematics; Function (biology); Algorithm; Computer science; Artificial intelligence; Geometry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001108521,0.0006977976,0.0008327616,0.0006897358,0.0003930551,0.0009263685,0.0008293178,0.0009792084,0.001058738],"category_scores_gemma":[0.003980392,0.0002701939,0.0004580004,0.000593814,0.0005892296,0.001444274,0.0005812005,0.0006996902,0.0004546133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007245147,"about_ca_system_score_gemma":0.0005296203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003576423,"about_ca_topic_score_gemma":0.003056349,"domain_scores_codex":[0.9995444,0.0001122354,0.00003250651,0.0001142222,0.0001433585,0.00005324368],"domain_scores_gemma":[0.999239,0.0003623907,0.00008160482,0.000124244,0.000166683,0.00002617616],"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":[0.0003149049,0.0001246745,0.001837862,0.000151212,0.0001115077,0.0002123097,0.0001231848,0.5298782,0.03533345,0.01081579,0.002824995,0.418272],"study_design_scores_gemma":[0.000004369524,0.0000250894,0.0002565386,0.000004052889,0.000006829784,0.00003525447,0.000003197641,0.9930151,0.004276757,0.001902903,0.0004647414,0.000005207751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06252848,0.0008242452,0.9329815,0.0002387364,0.0001140245,0.00003132986,0.00003718001,0.001142704,0.002101894],"genre_scores_gemma":[0.6709873,0.0004545696,0.3249955,0.0001832243,0.0000929847,0.0000546816,0.0001114925,0.0001874701,0.002932754],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003576423,"threshold_uncertainty_score":0.007111192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04066706910852975,"score_gpt":0.2923875884603741,"score_spread":0.2517205193518444,"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."}}