{"id":"W2106439909","doi":"10.1162/neco_a_00158","title":"Quickly Generating Representative Samples from an RBM-Derived Process","year":2011,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Gibbs sampling; Herding; Sampling (signal processing); Exploit; Markov chain; Computer science; Algorithm; Markov process; Mixing (physics); Process (computing); Divergence (linguistics); Mathematics; Artificial intelligence; Machine learning; Statistics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002616211,0.0006409134,0.001015102,0.0006250362,0.000422551,0.0008311781,0.001442227,0.001283279,0.001515336],"category_scores_gemma":[0.008812288,0.0005619525,0.0006681466,0.0003888623,0.001267996,0.001379647,0.001701839,0.001655634,0.0004031121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009354963,"about_ca_system_score_gemma":0.0008883384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001717919,"about_ca_topic_score_gemma":0.002547526,"domain_scores_codex":[0.9994654,0.0002009963,0.0000188724,0.0001254177,0.000138741,0.00005071844],"domain_scores_gemma":[0.9960413,0.00285918,0.0002227987,0.0004920232,0.0002624945,0.0001222138],"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":[0.0003001103,0.000113183,0.003457656,0.0001263534,0.00007254441,0.000196829,0.0003299238,0.8226384,0.01180948,0.07578752,0.001526626,0.08364137],"study_design_scores_gemma":[0.00001022364,0.00001458242,0.00009542373,0.000005367112,0.00000360685,0.00001873817,0.000006058879,0.9902961,0.001340995,0.008010442,0.0001945703,0.000003961508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04104234,0.0000909872,0.9574982,0.000153601,0.00001768196,0.00004870575,0.0000338027,0.0003357552,0.0007790011],"genre_scores_gemma":[0.6818053,0.0001134216,0.314838,0.000205664,0.00004499959,0.0002070157,0.0002916017,0.0001413748,0.002352673],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002616211,"threshold_uncertainty_score":0.01383603,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07464532759247174,"score_gpt":0.3044249065450997,"score_spread":0.229779578952628,"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."}}