{"id":"W2184456254","doi":"","title":"Fast Inference and Learning for Modeling Documents with a Deep Boltzmann Machine","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Softmax function; Boltzmann machine; Restricted Boltzmann machine; Inference; Computer science; Artificial intelligence; Machine learning; Deep learning; Layer (electronics); Boltzmann constant; Natural language processing; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0001074095,0.000105475,0.000109195,0.00003437758,0.0001996232,0.0003280334,0.0001888756,0.00002203494,0.00003074436],"category_scores_gemma":[0.00003309422,0.00007216162,0.00001817499,0.00008307246,0.00001787529,0.0008025971,0.0001231209,0.00007907682,0.00001164057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007707871,"about_ca_system_score_gemma":0.00001279552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003799573,"about_ca_topic_score_gemma":0.00006721119,"domain_scores_codex":[0.9993096,0.00003331819,0.0001016682,0.0002604445,0.00009302263,0.0002019554],"domain_scores_gemma":[0.9995796,0.00007851396,0.00003351131,0.0001385817,0.00009939887,0.00007040498],"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":[0.00001391315,0.00003829273,0.002910094,0.00001888284,0.00005942911,0.000001452964,0.001075787,0.6602895,0.001097124,0.005607659,0.0001863766,0.3287015],"study_design_scores_gemma":[0.0002565949,0.0001034011,0.000181382,0.000009551219,0.000004091451,0.000001792243,0.00005547775,0.9978416,0.0001936026,0.00105329,0.0001831119,0.0001161343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01257215,0.0000727099,0.9854745,0.000381101,0.00003293508,0.0002160425,1.542136e-7,0.00005405628,0.001196371],"genre_scores_gemma":[0.7414037,0.00001062074,0.2578331,0.0001393912,0.00002454056,0.00003567408,0.000001046353,0.00000490877,0.0005470382],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7288315,"threshold_uncertainty_score":0.3163234,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01134422252097587,"score_gpt":0.2277264320136763,"score_spread":0.2163822094927004,"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."}}