{"id":"W4320917681","doi":"10.3390/math11040977","title":"AutoGAN: An Automated Human-Out-of-the-Loop Approach for Training Generative Adversarial Networks","year":2023,"lang":"en","type":"article","venue":"Mathematics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Task (project management); Adversarial system; Artificial intelligence; Oversampling; Set (abstract data type); Process (computing); Machine learning; Generative grammar; Training (meteorology); Point (geometry); Artificial neural network; Modalities; Quality (philosophy); Training set; Mathematics","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":[0.0007710085,0.0002334697,0.0003908616,0.00008450235,0.0004475986,0.0001517545,0.0010519,0.0001265213,0.000006513402],"category_scores_gemma":[0.0001345019,0.0001765079,0.000196049,0.0006432588,0.0001032548,0.0003247226,0.0002760217,0.0001282426,0.000005353891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003123822,"about_ca_system_score_gemma":0.00007894571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004262875,"about_ca_topic_score_gemma":0.000006745043,"domain_scores_codex":[0.998284,0.0001311605,0.0004607937,0.0003956372,0.0002916343,0.0004367333],"domain_scores_gemma":[0.9985514,0.0002034399,0.0002838176,0.0007279984,0.0001478756,0.00008542686],"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":[0.00001467849,0.0004712985,0.00002675156,0.0001990761,0.0003249568,0.000005271421,0.03632044,0.8124141,0.01632392,0.1049578,0.01817207,0.01076959],"study_design_scores_gemma":[0.0004241333,0.00008323998,0.00004817317,0.00002721498,0.00003449282,0.000001683694,0.0004419879,0.9921215,0.002610832,0.003717321,0.00028028,0.0002091499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00406082,0.00001274713,0.9926733,0.0001288925,0.0009857789,0.0006220802,0.00001043306,0.0006166739,0.000889286],"genre_scores_gemma":[0.3598811,0.000002781728,0.6384525,0.0001078454,0.0005693922,0.0001154365,0.00003590133,0.00004430582,0.0007907621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3558203,"threshold_uncertainty_score":0.7197784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0761518601387779,"score_gpt":0.3085738216193072,"score_spread":0.2324219614805293,"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."}}