{"id":"W3122717230","doi":"10.1109/scisisis50064.2020.9322714","title":"Unsupervised Feature Learning for Output Control of Generative Models","year":2020,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Global Institution for Collaborative Research and Education, Hokkaido University; Japan Society for the Promotion of Science; Hokkaido University; Telecommunications Advancement Foundation; Institute for Catastrophic Loss Reduction","keywords":"Artificial intelligence; Computer science; Cluster analysis; Generative model; Class (philosophy); Pattern recognition (psychology); Generative grammar; Unsupervised learning; Point (geometry); Feature (linguistics); Data modeling; Machine learning; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001204941,0.0008701377,0.0007768335,0.0003649837,0.0003733851,0.001013263,0.001252933,0.0008667128,0.00349425],"category_scores_gemma":[0.004225925,0.0005484199,0.0007756974,0.0004188919,0.001446494,0.001268802,0.001547764,0.002170651,0.0005189988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234354,"about_ca_system_score_gemma":0.0009167918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002817385,"about_ca_topic_score_gemma":0.004028083,"domain_scores_codex":[0.9995572,0.0001202531,0.00001765765,0.0001468501,0.0001015104,0.00005653673],"domain_scores_gemma":[0.9987489,0.0008107474,0.0001151741,0.0001476456,0.0001364204,0.00004107598],"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":[0.00005461938,0.00002431203,0.0002345261,0.0000550039,0.00002877163,0.00003596993,0.00005590718,0.8739433,0.003005879,0.08281336,0.001412789,0.03833556],"study_design_scores_gemma":[0.000002917511,0.000006752093,0.00002452257,0.00000365097,0.000002042557,0.000005293964,0.000001549106,0.9863626,0.0004264679,0.0127431,0.0004182626,0.00000284872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003286137,0.0001269551,0.9949078,0.0001052608,0.00001506565,0.00001128576,0.00003853721,0.0002110861,0.001297891],"genre_scores_gemma":[0.8185344,0.0004259066,0.1726707,0.0002172573,0.00008507595,0.0002205158,0.0002946685,0.0003723673,0.00717914],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00349425,"threshold_uncertainty_score":0.01168948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03299584363253637,"score_gpt":0.2239093068096609,"score_spread":0.1909134631771245,"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."}}