{"id":"W3035353183","doi":"","title":"Small-GAN: Speeding up GAN Training using Core-Sets","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Toronto","funders":"","keywords":"Computer science; Selection (genetic algorithm); Training (meteorology); Cache; Core (optical fiber); Fraction (chemistry); Machine learning; Artificial intelligence; Generative grammar; Training set; Parallel computing","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":[0.0001781949,0.0001721646,0.0001585336,0.0001267279,0.000242744,0.0002944567,0.000884045,0.00006176491,0.0002754402],"category_scores_gemma":[0.0001364922,0.0001775845,0.00008126043,0.000264658,0.0000339748,0.0002482444,0.0001459701,0.0005368768,0.00008333612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006086313,"about_ca_system_score_gemma":0.00006736373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006671909,"about_ca_topic_score_gemma":0.000005391072,"domain_scores_codex":[0.9987141,0.00003989985,0.0002700474,0.0004538178,0.0003076161,0.0002145109],"domain_scores_gemma":[0.999292,0.00005912483,0.0001956775,0.0001631419,0.000152344,0.0001377545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004395929,0.00004969856,0.003813603,0.0000145144,0.00007374168,0.00003458988,0.004103678,0.01181782,0.05594751,0.7353928,0.0001561792,0.1885519],"study_design_scores_gemma":[0.0001969267,0.0001170149,0.0003304733,0.00003871782,0.000004246751,0.00002589818,0.0001614794,0.9843449,0.002916303,0.00261104,0.009047042,0.0002059516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05002879,0.00001347857,0.9167237,0.006381056,0.0003069361,0.0001328397,0.000005979194,0.0005628659,0.0258444],"genre_scores_gemma":[0.9700983,0.00001657035,0.02826011,0.001066625,0.0001846627,0.00001075216,0.00001349787,0.00001651892,0.0003329797],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9725271,"threshold_uncertainty_score":0.7241685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2740616492013114,"score_gpt":0.3543970622550278,"score_spread":0.08033541305371639,"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."}}