{"id":"W4402471162","doi":"10.31219/osf.io/d97b3","title":"Backpropagation and Optimization in Deep Learning: Tutorial and Survey","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Backpropagation; Gradient descent; Stochastic gradient descent; Artificial neural network; Convergence (economics); Computer science; Parameterized complexity; Mathematical optimization; Minification; Stochastic optimization; Method of steepest descent; Deep learning; Momentum (technical analysis); Artificial intelligence; Algorithm; Mathematics","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":[0.001349254,0.002148848,0.001795786,0.001921166,0.000381106,0.001935135,0.001384436,0.002278659,0.007796581],"category_scores_gemma":[0.003237185,0.001209222,0.0009344015,0.006259002,0.001287518,0.004281825,0.001595999,0.003980137,0.005918069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009853528,"about_ca_system_score_gemma":0.001336434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001606752,"about_ca_topic_score_gemma":0.001346689,"domain_scores_codex":[0.9989807,0.0001814393,0.0001042468,0.0002215194,0.0004559454,0.00005613304],"domain_scores_gemma":[0.9990891,0.0005880408,0.00005071033,0.00007898109,0.000156655,0.0000365436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007060145,0.000156341,0.0006502758,0.004322795,0.0001534748,0.0001429518,0.0001460136,0.02521454,0.00169486,0.1158917,0.07231988,0.7792365],"study_design_scores_gemma":[0.00002942403,0.0001414193,0.001122614,0.001514806,0.00008810267,0.0007064321,0.00006267156,0.05846198,0.003183904,0.2255971,0.7089912,0.0001002866],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001721463,0.5973595,0.3748048,0.002418684,0.002739088,0.00007770888,0.0004294786,0.0007985948,0.01965068],"genre_scores_gemma":[0.02722409,0.7562646,0.1817888,0.002207138,0.006761346,0.0003134172,0.001411918,0.0008479463,0.02318087],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.007796581,"threshold_uncertainty_score":0.02608216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01936290719349731,"score_gpt":0.2564613445579478,"score_spread":0.2370984373644505,"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."}}