{"id":"W2607390531","doi":"10.1007/s40687-018-0148-y","title":"Deep relaxation: partial differential equations for optimizing deep neural networks","year":2018,"lang":"en","type":"preprint","venue":"Research in the Mathematical Sciences","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Air Force Office of Scientific Research; Army Research Office; Office of Naval Research; Simons Foundation; U.S. Department of Energy","keywords":"Curse of dimensionality; Partial differential equation; Artificial neural network; Nonlinear system; Computer science; Homogenization (climate); Relaxation (psychology); Stochastic gradient descent; Applied mathematics; Context (archaeology); Stochastic partial differential equation; Mathematical optimization; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003160462,0.0001948127,0.0002705546,0.0001369694,0.0008960647,0.0006534897,0.001111349,0.000124503,0.0007255521],"category_scores_gemma":[0.000148231,0.0001204939,0.0001825819,0.0004906927,0.0009344156,0.0001224567,0.0005263626,0.0009609394,0.00002324417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003669969,"about_ca_system_score_gemma":0.00007005392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002889502,"about_ca_topic_score_gemma":0.00000508177,"domain_scores_codex":[0.996806,0.0005799624,0.0004449578,0.0005224604,0.0008921879,0.0007543888],"domain_scores_gemma":[0.9971108,0.002099924,0.0001407557,0.0003857735,0.0001423776,0.0001203868],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004002438,0.0003585886,0.00006393489,0.000087428,0.00003504189,0.00000111545,0.001457171,0.4286326,0.000007919513,0.5514212,0.0008147506,0.01708026],"study_design_scores_gemma":[0.0001046333,0.00005943199,0.000009676087,0.00005803953,0.000009375045,6.92494e-7,0.0004243821,0.7672774,0.00001476043,0.2319037,0.00003100181,0.0001069215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01744377,0.00007022874,0.974122,0.002156354,0.0004676961,0.00116441,0.000004665651,0.00002188533,0.004548965],"genre_scores_gemma":[0.9928388,0.000005664812,0.004030788,0.00002085933,0.002304584,0.000679765,0.00002634069,0.00001304338,0.00008016436],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.975395,"threshold_uncertainty_score":0.7944287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2019696259217802,"score_gpt":0.422924077972178,"score_spread":0.2209544520503978,"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."}}