{"id":"W1738389294","doi":"10.48550/arxiv.1412.6617","title":"Understanding Minimum Probability Flow for RBMs Under Various Kinds of Dynamics","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Boltzmann machine; Divergence (linguistics); Computer science; Importance sampling; Partition function (quantum field theory); Artificial intelligence; Sampling (signal processing); Function (biology); Dynamics (music); Restricted Boltzmann machine; Gibbs sampling; Flow (mathematics); Monte Carlo method; Artificial neural network; Machine learning; Statistical physics; Mathematics; Statistics; Physics; Bayesian probability","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000550974,0.0003600308,0.0005531783,0.0001880257,0.0001972365,0.0001101602,0.001441681,0.0003605921,0.00001197485],"category_scores_gemma":[0.00007557845,0.0003954273,0.0003867623,0.0003835629,0.0002136306,0.0002598134,0.001203308,0.000325939,0.000004254973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006924762,"about_ca_system_score_gemma":0.0002584999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000074887,"about_ca_topic_score_gemma":0.0002112384,"domain_scores_codex":[0.9977819,0.000214226,0.0003187986,0.001154134,0.0001142419,0.0004166533],"domain_scores_gemma":[0.9975455,0.0003951325,0.0004091904,0.001249215,0.0002606745,0.0001403249],"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":[0.00003164998,0.00007323358,0.0001952625,0.0001113368,0.000112681,0.000005124628,0.00009660181,0.7523459,0.00001836623,0.2466167,0.0001702941,0.0002229112],"study_design_scores_gemma":[0.0003495209,0.00007257436,0.00008844979,0.00005178837,0.0000739259,7.04468e-7,0.00005006211,0.7003623,0.00006830187,0.2985608,0.00004030197,0.0002813121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006634796,0.00002142638,0.9903371,0.0001980991,0.0009038683,0.0006011245,0.00004870507,0.00009711525,0.001157786],"genre_scores_gemma":[0.9570973,0.00002786873,0.04234133,0.0000677324,0.0001017689,0.000002270613,0.00002877953,0.00002168807,0.0003112966],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9504625,"threshold_uncertainty_score":0.9998497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1477047935370241,"score_gpt":0.1976206267071002,"score_spread":0.04991583317007603,"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."}}