{"id":"W2274603360","doi":"10.71781/10876","title":"Improving sampling, optimization and feature extraction in Boltzmann machines","year":2013,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Boltzmann machine; Sampling (signal processing); Computer science; Extraction (chemistry); Feature (linguistics); Restricted Boltzmann machine; Artificial intelligence; Data mining; Pattern recognition (psychology); Statistics; Machine learning; Mathematics; Chromatography; Chemistry; Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002078144,0.0002042488,0.0002307467,0.0001290371,0.0001264599,0.001176327,0.0005073796,0.0002146892,0.0002059739],"category_scores_gemma":[0.00005637305,0.0001892623,0.00003030923,0.0001818345,0.000009482991,0.001361215,0.0001314358,0.000240532,0.00002353764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003247401,"about_ca_system_score_gemma":0.00007090521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004880418,"about_ca_topic_score_gemma":0.0008321587,"domain_scores_codex":[0.9989039,0.00006497493,0.0002003579,0.0005351203,0.0001231452,0.0001724481],"domain_scores_gemma":[0.9993298,0.00004774379,0.0002340619,0.0002520004,0.00008643119,0.00004995941],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001512304,0.0000325062,0.00006191246,0.00001940141,0.00001462126,0.00000446231,0.0009304855,0.02137026,0.003507473,0.00002389886,0.0004302789,0.9735896],"study_design_scores_gemma":[0.0003200089,0.00004178331,0.002492287,0.0001518447,0.00002307354,0.000005796485,0.0002209832,0.988673,0.003192122,0.00008138814,0.004393368,0.0004042842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03721046,0.001422848,0.9447775,0.0004017418,0.002100053,0.001651268,0.00001162547,0.00001027862,0.01241417],"genre_scores_gemma":[0.04046766,0.000174821,0.9369963,0.0000409962,0.0002725214,0.00006789052,0.0004640903,0.00003240142,0.02148329],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9731853,"threshold_uncertainty_score":0.9998605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02103416931475968,"score_gpt":0.2961940343017991,"score_spread":0.2751598649870395,"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."}}