{"id":"W2963622136","doi":"","title":"Bidirectional Helmholtz machines","year":2016,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"","keywords":"Inference; Autoencoder; Generative model; Computer science; Helmholtz free energy; Fiducial inference; Algorithm; Artificial intelligence; Bhattacharyya distance; Generative grammar; Frequentist inference; Machine learning; Bayesian inference; Deep learning; Bayesian probability","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":[0.00164123,0.001052101,0.001253401,0.001021424,0.0008936266,0.001501524,0.001965246,0.002138375,0.007251407],"category_scores_gemma":[0.007709518,0.0009573208,0.001458108,0.000959437,0.002345203,0.003092137,0.003693792,0.002353824,0.002255406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001264327,"about_ca_system_score_gemma":0.001168584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001899046,"about_ca_topic_score_gemma":0.003091865,"domain_scores_codex":[0.9988645,0.0004129397,0.00004691509,0.0002873013,0.0002565228,0.0001318027],"domain_scores_gemma":[0.9981225,0.001151177,0.0001483829,0.0003241157,0.000151334,0.0001024749],"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":[0.00007919061,0.00003134373,0.0004998697,0.0001065352,0.00004966684,0.00008550772,0.0001566348,0.475684,0.003245614,0.4614032,0.002720594,0.05593786],"study_design_scores_gemma":[0.000006643569,0.00001125239,0.0000650096,0.0000157014,0.000005739591,0.00003471827,0.00001286897,0.7512513,0.001058097,0.2457278,0.001796749,0.00001405353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007058033,0.0002294528,0.9870923,0.0002951227,0.00003266659,0.00002854719,0.0001670972,0.0005823646,0.004514406],"genre_scores_gemma":[0.5331315,0.0009216553,0.4408225,0.0007913299,0.0001987674,0.0004074729,0.0009170401,0.0009410804,0.02186861],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007251407,"threshold_uncertainty_score":0.02425838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02976715096329061,"score_gpt":0.275138694609757,"score_spread":0.2453715436464664,"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."}}