{"id":"W1779483307","doi":"10.48550/arxiv.1509.00519","title":"Importance Weighted Autoencoders","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":251,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Autoencoder; Inference; Posterior probability; Computer science; Weighting; Artificial intelligence; Generative grammar; Pattern recognition (psychology); Generative model; Flexibility (engineering); Machine learning; Algorithm; Artificial neural network; Mathematics; Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003501855,0.0003847224,0.0004107411,0.0001787597,0.0001554086,0.0001845307,0.002190334,0.0002542522,0.00004892339],"category_scores_gemma":[0.00004115426,0.0004165193,0.0002324601,0.0006013861,0.0001266349,0.0005559375,0.001936894,0.0005202055,0.0001451436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002725224,"about_ca_system_score_gemma":0.0004394111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001554189,"about_ca_topic_score_gemma":0.00008142638,"domain_scores_codex":[0.9976849,0.0001986086,0.0002302794,0.001306744,0.0001306662,0.0004487951],"domain_scores_gemma":[0.9974789,0.00006395,0.0002996845,0.001542329,0.0003222998,0.0002928603],"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":[0.00002370869,0.00009557982,0.001896494,0.00002990677,0.0001802781,0.0005708057,0.0002887643,0.932151,0.00001869186,0.04486755,0.01843174,0.001445515],"study_design_scores_gemma":[0.0002895808,0.00003133921,0.0003811607,0.00003431186,0.00004539322,0.000002824316,0.00003232553,0.9360586,0.00007985066,0.05970411,0.002866377,0.0004740786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02098915,0.0001543306,0.9676859,0.0002684942,0.00115968,0.0002430944,0.0000138526,0.0003308291,0.009154609],"genre_scores_gemma":[0.9783599,0.0001344136,0.0186411,0.0001914623,0.0002007711,0.000001092376,0.00001862612,0.00002110577,0.002431506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9573708,"threshold_uncertainty_score":0.9998286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07168787938815764,"score_gpt":0.1866033410959169,"score_spread":0.1149154617077593,"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."}}