{"id":"W3023788528","doi":"10.1016/j.neunet.2020.04.029","title":"Multi-projection of unequal dimension optimal transport theory for Generative Adversary Networks","year":2020,"lang":"en","type":"article","venue":"Neural Networks","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Wasserstein metric; Linear subspace; Dimension (graph theory); Metric (unit); Projection (relational algebra); Generative model; Generative grammar; Mathematical optimization; Parameterized complexity; Differentiable function; Probability distribution; Mathematics; Intrinsic dimension; Artificial intelligence; Algorithm; Applied 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003781979,0.0003359834,0.0004644011,0.00005565113,0.0002505242,0.00004891061,0.0005619576,0.0001968112,0.00001635549],"category_scores_gemma":[0.00004909801,0.0002951749,0.0003069269,0.0005164854,0.0001118396,0.000585754,0.0001373681,0.0003161514,0.000001577476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002649481,"about_ca_system_score_gemma":0.00003917854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001498352,"about_ca_topic_score_gemma":0.000008521032,"domain_scores_codex":[0.9977391,0.0002944713,0.0005156538,0.0007196052,0.000225479,0.0005056437],"domain_scores_gemma":[0.9987023,0.000303389,0.0002569499,0.0003417096,0.0001964458,0.0001992295],"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":[0.0002780162,0.00005870155,0.0001384007,0.0000119004,0.000063363,0.00000873022,0.0005433028,0.9656178,0.001907396,0.0008814863,0.0008009277,0.02968991],"study_design_scores_gemma":[0.0009672325,0.0005199389,0.0004653031,0.00001778616,0.00005176603,0.000002782908,0.00007428924,0.9950728,0.002199335,0.00004076051,0.0002832712,0.0003047762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006720505,0.0006137668,0.9901254,0.0006355869,0.001028831,0.0006730243,0.00001050062,0.0001467557,0.00004563733],"genre_scores_gemma":[0.8841546,0.00006305787,0.1134712,0.001223064,0.000932381,0.00004333017,0.00003816047,0.00003116125,0.00004301558],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8774341,"threshold_uncertainty_score":0.9999501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02926115820066098,"score_gpt":0.2457177283926195,"score_spread":0.2164565701919586,"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."}}