{"id":"W2624918116","doi":"10.1142/s0219633617300014","title":"Fitting potential energy surfaces to sum-of-products form with neural networks using exponential neurons","year":2017,"lang":"en","type":"article","venue":"Journal of Theoretical and Computational Chemistry","topic":"Spectroscopy and Quantum Chemical Studies","field":"Physics and Astronomy","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Uppsala Universitet; Compute Canada","keywords":"Ab initio; Artificial neural network; Hartree; Exponential function; Potential energy; Quantum; Statistical physics; Potential energy surface; Computer science; MATLAB; Computational physics; Computational chemistry; Physics; Chemistry; Quantum mechanics; Mathematics; Artificial intelligence; Mathematical analysis","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00008022565,0.000108078,0.0002102812,0.00001008136,0.0002330101,0.00007150458,0.0001584874,0.00002395908,0.00005428322],"category_scores_gemma":[0.00002266968,0.00007912287,0.00006650807,0.00002993967,0.0002982903,0.00008894515,0.0001052232,0.0001389986,6.130387e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008012297,"about_ca_system_score_gemma":0.00002732748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001090999,"about_ca_topic_score_gemma":5.988606e-8,"domain_scores_codex":[0.9992908,0.00001060346,0.0002445087,0.0001188656,0.0001867938,0.0001484784],"domain_scores_gemma":[0.99931,0.00007471357,0.0002832627,0.00007736686,0.0001577309,0.0000969127],"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":[0.002878867,0.0007378828,0.02899816,0.0001836916,0.00104757,0.00008233992,0.0003047065,0.4976428,0.2728121,0.1854965,0.000361786,0.00945361],"study_design_scores_gemma":[0.002230551,0.0004087912,0.007456727,0.0002687751,0.0003202618,0.000192999,0.0003560226,0.5059069,0.2999196,0.1822974,0.00006423477,0.0005777698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.964793,0.00005289496,0.03418987,0.000528413,0.00007454482,0.00001757473,0.00000686167,0.000002320368,0.0003344715],"genre_scores_gemma":[0.9972439,0.000001429135,0.002116109,0.00002227276,0.0005975489,4.871778e-7,0.0000033365,0.000007114718,0.000007779369],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03245087,"threshold_uncertainty_score":0.3226537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008022185610491134,"score_gpt":0.2442081367914553,"score_spread":0.2361859511809642,"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."}}