{"id":"W2910857484","doi":"10.48550/arxiv.1901.08680","title":"Multi-objective training of Generative Adversarial Networks with multiple discriminators","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Institut National de la Recherche Scientifique; McGill University; Université du Québec","funders":"","keywords":"Discriminator; Maximization; Computer science; Adversarial system; Gradient descent; Mathematical optimization; Generative grammar; Minification; Generator (circuit theory); Multi-objective optimization; Leverage (statistics); Artificial intelligence; Machine learning; Algorithm; Mathematics; Artificial neural network","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":[],"consensus_categories":[],"category_scores_codex":[0.00007371281,0.0001138083,0.000148793,0.00009137293,0.000102001,0.0000171386,0.0004040212,0.00006271206,0.00001256396],"category_scores_gemma":[0.000005906609,0.0001077762,0.00006685329,0.0005712894,0.00007895906,0.0003522443,0.000117053,0.0001205259,0.000009660078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005428233,"about_ca_system_score_gemma":0.00005037749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009249015,"about_ca_topic_score_gemma":0.00005126935,"domain_scores_codex":[0.9992446,0.00004163611,0.00009592914,0.0004056723,0.00004459186,0.0001675667],"domain_scores_gemma":[0.9992809,0.00006394805,0.000126507,0.0003709246,0.00009464478,0.00006307678],"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":[0.000182622,0.0003145426,0.03993816,0.00001876248,0.0001757971,0.00003713614,0.003899929,0.5394032,0.003563806,0.4078127,0.00006822342,0.004585119],"study_design_scores_gemma":[0.000816962,0.0002036954,0.005890228,0.00001388773,0.00001733811,0.00000292626,0.0007841712,0.9880658,0.003356338,0.0005478761,0.0001155134,0.0001852713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.281813,0.000003187573,0.7172129,0.00001100199,0.00005189153,0.0001877644,0.000002120073,0.00009458918,0.0006235118],"genre_scores_gemma":[0.9760293,0.000006378358,0.02343607,0.00002586565,0.00001811392,0.000001688705,0.000001817275,0.000007467593,0.0004732585],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6942163,"threshold_uncertainty_score":0.4394988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04352341204201671,"score_gpt":0.1794360343879172,"score_spread":0.1359126223459005,"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."}}