{"id":"W4318977988","doi":"10.1007/978-3-031-10602-6_20","title":"Variational Autoencoders","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Discriminative model; Inference; Generative model; Latent variable; Upper and lower bounds; Expectation–maximization algorithm; Artificial intelligence; Maximization; Computer science; Bayesian inference; Pattern recognition (psychology); Backpropagation; Artificial neural network; Generative grammar; Algorithm; Mathematics; Bayesian probability; Maximum likelihood; Mathematical optimization; Statistics","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":[0.0003263698,0.0007650141,0.0006156145,0.0003590031,0.0002489036,0.0009673676,0.0006860057,0.0007957185,0.01973619],"category_scores_gemma":[0.001016534,0.0004383839,0.0003479759,0.0005583612,0.000627991,0.001201456,0.0009725036,0.001504932,0.008134995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005403089,"about_ca_system_score_gemma":0.0004209884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001696234,"about_ca_topic_score_gemma":0.003526949,"domain_scores_codex":[0.9998522,0.00002824373,0.000004927488,0.00003547933,0.00006921666,0.000009994186],"domain_scores_gemma":[0.9998477,0.00006712761,0.000006267931,0.0000379534,0.00003333818,0.00000755339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002138093,0.00002674371,0.0001401231,0.0001708491,0.00004721308,0.00003383867,0.00005453921,0.07731862,0.002342444,0.4157895,0.08861268,0.4154421],"study_design_scores_gemma":[0.000006573683,0.00002203197,0.0003846453,0.0001040196,0.0000238705,0.0001219714,0.00002309987,0.3207018,0.00362464,0.4168735,0.2580864,0.00002746605],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.002482348,0.008589852,0.8220379,0.001095235,0.0008640087,0.00002848629,0.00042594,0.0008602308,0.1636159],"genre_scores_gemma":[0.1128808,0.01386262,0.2582723,0.0007854937,0.001136721,0.000144686,0.001827425,0.001555966,0.609534],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01973619,"threshold_uncertainty_score":0.06602418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02032279413806279,"score_gpt":0.2204618980364453,"score_spread":0.2001391038983825,"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."}}