{"id":"W1876224860","doi":"10.48550/arxiv.1203.4416","title":"On Training Deep Boltzmann Machines","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Boltzmann machine; Regularization (linguistics); Boltzmann constant; Computer science; Artificial intelligence; Probabilistic logic; Restricted Boltzmann machine; Machine learning; Deep learning; Training (meteorology); Physics","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":[0.0002838183,0.0003878309,0.000376485,0.0001997966,0.0002008015,0.0001606717,0.001609595,0.0002487143,0.00009368773],"category_scores_gemma":[0.00005039693,0.0004030338,0.0002684043,0.0003466858,0.00008317339,0.0004473023,0.001307038,0.0005655225,0.0001973603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001123327,"about_ca_system_score_gemma":0.00008770107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007210922,"about_ca_topic_score_gemma":0.00003488262,"domain_scores_codex":[0.9980119,0.0002193637,0.0001750258,0.0009788162,0.000104215,0.0005106464],"domain_scores_gemma":[0.9981867,0.0001824584,0.0002085835,0.001103956,0.00009248904,0.0002258168],"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":[0.00002337896,0.0001012326,0.0003054978,0.00002371187,0.0001305388,0.0001305959,0.0008229986,0.8127497,0.0000394179,0.1682628,0.0007558269,0.01665432],"study_design_scores_gemma":[0.0002666319,0.00003990429,0.0007309322,0.00005911473,0.00005847722,0.000003002905,0.00004170632,0.9563065,0.0001015952,0.04063421,0.001227152,0.0005307908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0220665,0.0001629396,0.9656881,0.0001467285,0.001540967,0.0001900912,0.000007648346,0.000212188,0.009984837],"genre_scores_gemma":[0.992454,0.00007838944,0.005606625,0.0002739023,0.0003918439,0.000001030104,0.00001106027,0.00002246192,0.001160676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9703875,"threshold_uncertainty_score":0.9998422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08224779654064972,"score_gpt":0.1899034966123352,"score_spread":0.1076557000716854,"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."}}