{"id":"W2963812505","doi":"","title":"DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"D-Wave Systems (Canada)","funders":"","keywords":"Boltzmann machine; MNIST database; Prior probability; Restricted Boltzmann machine; Gaussian; Computer science; Binary number; Upper and lower bounds; Artificial intelligence; Boltzmann constant; Algorithm; Autoencoder; Boltzmann distribution; Mathematics; Pattern recognition (psychology); Artificial neural network; Statistical physics; Bayesian probability; Physics; Mathematical analysis","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":[0.001672479,0.0009191691,0.0009802124,0.0004518724,0.000337791,0.001168196,0.002873352,0.001594264,0.007072215],"category_scores_gemma":[0.0057989,0.0007246176,0.0008303947,0.0005693351,0.001065377,0.002154371,0.002789832,0.003442366,0.00243941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009541801,"about_ca_system_score_gemma":0.0009552799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003351263,"about_ca_topic_score_gemma":0.006753508,"domain_scores_codex":[0.9991018,0.0003102104,0.00004596496,0.000205994,0.0002556883,0.00008038073],"domain_scores_gemma":[0.9990213,0.0004967761,0.00005668912,0.0002484481,0.0001170407,0.0000597137],"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":[0.0001788811,0.00009258521,0.0006706908,0.0001527835,0.0001449703,0.00009110497,0.00009779601,0.6583911,0.005245142,0.1001416,0.01287971,0.2219136],"study_design_scores_gemma":[0.00001819843,0.00001522766,0.00005410782,0.000009940944,0.000005401953,0.00002516622,0.000004757696,0.9716542,0.001665985,0.02337186,0.003167508,0.000007568356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003809487,0.0002244007,0.9918247,0.0002367746,0.00008417224,0.00004205709,0.0001909787,0.001480809,0.002106587],"genre_scores_gemma":[0.2839862,0.0004860776,0.6971795,0.0007878461,0.0001346598,0.0004063484,0.001608282,0.00122489,0.01418622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007072215,"threshold_uncertainty_score":0.02365887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02863410500574351,"score_gpt":0.1642277174748586,"score_spread":0.1355936124691151,"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."}}