{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003996955,0.0001212758,0.0001606815,0.0002912998,0.001513458,0.00006872608,0.0001959632,0.00003001945,0.00006716687],"category_scores_gemma":[0.00001237394,0.0001141039,0.00001728224,0.0009350203,0.0005121064,0.0002101258,0.0003188041,0.0007245883,1.388269e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002854401,"about_ca_system_score_gemma":0.00004273526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006313401,"about_ca_topic_score_gemma":0.000006326125,"domain_scores_codex":[0.9988844,0.00006973135,0.0001205975,0.0003995857,0.0001711972,0.0003544722],"domain_scores_gemma":[0.9996367,0.00001863195,0.00008443993,0.0001269992,0.00004480615,0.0000884882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003527964,0.00004799294,0.02521182,0.000001581087,0.00002430207,0.00001844167,0.0009198894,0.4590821,0.001886891,0.04861161,0.00001271186,0.4641474],"study_design_scores_gemma":[0.0001750857,0.0002611734,0.0001520135,0.000001906448,0.00001188951,0.00007285598,0.002978743,0.9946417,0.00002677122,0.0008882025,0.0006620839,0.0001275386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908459,0.0002643658,0.007713728,0.0004637257,0.000155215,0.00009226211,0.000003675046,0.00009716842,0.0003640127],"genre_scores_gemma":[0.9990755,0.000004207135,0.0006692399,0.00006483337,0.00009355781,0.00001247794,0.000002013235,0.00001099672,0.0000671478],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5355596,"threshold_uncertainty_score":0.9997864,"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."}}