{"id":"W1579917626","doi":"10.48550/arxiv.1301.3545","title":"Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Hessian matrix; Boltzmann machine; Metric (unit); Mathematics; Computer science; Mathematical optimization; Algorithm; Gradient method; Applied mathematics; Artificial intelligence; Deep learning; Engineering","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":[0.001977105,0.001320405,0.00125837,0.0006510293,0.0005351191,0.001086471,0.002747705,0.001827241,0.005141059],"category_scores_gemma":[0.01105035,0.000758913,0.0007761809,0.0007249974,0.00113436,0.002229904,0.002258777,0.002703,0.002363375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001324436,"about_ca_system_score_gemma":0.001683146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00292849,"about_ca_topic_score_gemma":0.004155946,"domain_scores_codex":[0.9988292,0.0005480561,0.00006261669,0.0001639742,0.000316591,0.00007955024],"domain_scores_gemma":[0.998447,0.0007948209,0.00009677186,0.0002745565,0.0003084368,0.00007846217],"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":[0.0001683278,0.00007520534,0.0005504106,0.0001684704,0.00007157472,0.00007050444,0.0001232492,0.6987964,0.003074721,0.1088731,0.006001975,0.182026],"study_design_scores_gemma":[0.000007490448,0.00001414895,0.00002849268,0.000007366538,0.000002208097,0.00001515872,0.00000321245,0.9735901,0.0004586695,0.02493037,0.0009375602,0.000005118336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001902099,0.0001027167,0.9964746,0.00009571784,0.00002887366,0.0000291313,0.00002784825,0.0006016431,0.0007374273],"genre_scores_gemma":[0.1657843,0.0002163161,0.8278399,0.000272957,0.0000967064,0.0005031386,0.0003665405,0.0007273029,0.004192832],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005141059,"threshold_uncertainty_score":0.0171985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08939302955471162,"score_gpt":0.2025616082760093,"score_spread":0.1131685787212977,"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."}}