{"id":"W4310124277","doi":"10.1088/2632-2153/aca6cd","title":"Training neural networks using Metropolis Monte Carlo and an adaptive variant","year":2022,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Ottawa","funders":"Lawrence Berkeley National Laboratory; Basic Energy Sciences; U.S. Department of Energy","keywords":"Artificial neural network; Gradient descent; Monte Carlo method; Computer science; Complement (music); Metropolis–Hastings algorithm; Stochastic neural network; Artificial intelligence; Set (abstract data type); Algorithm; Stochastic gradient descent; Stability (learning theory); Monte Carlo algorithm; Function (biology); Machine learning; Time delay neural network; Markov chain Monte Carlo; 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":[0.002440457,0.000478347,0.0008122575,0.0005631177,0.0005510337,0.0009206583,0.002092937,0.000938305,0.001761609],"category_scores_gemma":[0.007705354,0.0005057488,0.0005928509,0.0007284852,0.001937909,0.00125555,0.0008879467,0.001554187,0.0002639279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00138792,"about_ca_system_score_gemma":0.001356526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008850642,"about_ca_topic_score_gemma":0.008126127,"domain_scores_codex":[0.9992234,0.0003997289,0.00003237234,0.0001000234,0.0001789399,0.00006556316],"domain_scores_gemma":[0.9964379,0.002633848,0.0001679662,0.0003436902,0.0003248899,0.00009179369],"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":[0.00007265922,0.00004124361,0.0007737101,0.00003841636,0.0000448454,0.00004337228,0.0000390977,0.9199803,0.001071313,0.06510864,0.0005060458,0.01228033],"study_design_scores_gemma":[0.000005269358,0.000005775811,0.00002390154,0.000001975531,0.000001449808,0.000002479672,0.000001234568,0.9959691,0.0002588138,0.003620025,0.0001080219,0.000002096302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04506496,0.0003047086,0.9501554,0.00036582,0.0000711305,0.00008171984,0.00002980265,0.0005397436,0.00338661],"genre_scores_gemma":[0.7208069,0.0002081066,0.2754925,0.0002355619,0.00007785489,0.0003076238,0.00008313939,0.0002600501,0.002528146],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008850642,"threshold_uncertainty_score":0.01759821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02592770553778241,"score_gpt":0.2769468053588732,"score_spread":0.2510190998210908,"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."}}