{"id":"W2949995983","doi":"10.48550/arxiv.1505.03906","title":"Training generative neural networks via Maximum Mean Discrepancy\\n optimization","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":222,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Artificial neural network; Artificial intelligence; Computer science","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":[0.0004372209,0.0005431044,0.0005624021,0.0002071686,0.0003214144,0.0003445167,0.00164633,0.0003682934,0.00004116672],"category_scores_gemma":[0.00003973878,0.0005834864,0.0002875343,0.0006832068,0.0001521776,0.0008764187,0.001823724,0.0006821562,0.00001382764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002568449,"about_ca_system_score_gemma":0.0002080293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001428718,"about_ca_topic_score_gemma":0.00008819134,"domain_scores_codex":[0.9969025,0.0005008654,0.0003237489,0.001513221,0.0001574469,0.0006022514],"domain_scores_gemma":[0.9975871,0.00009002515,0.0004048628,0.001177403,0.0004009288,0.0003396746],"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":[0.00002252244,0.00003984314,0.00005443614,0.000007538523,0.0001113739,0.0001305002,0.0007776786,0.9902427,0.000007116721,0.003643813,0.0003631804,0.004599262],"study_design_scores_gemma":[0.0003802587,0.00006576163,0.00002534804,0.00003533995,0.00008648272,0.000006326202,0.0001392139,0.9882996,0.00003527831,0.01017487,0.0001252424,0.0006262576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002364404,0.0001800945,0.9930975,0.0001608473,0.001672756,0.000381365,0.00001228428,0.0002784791,0.001852224],"genre_scores_gemma":[0.946556,0.00009958699,0.05195058,0.000181708,0.0005990079,0.000002686025,0.00007580975,0.00003759549,0.0004970356],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9441916,"threshold_uncertainty_score":0.9996617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.091277332981538,"score_gpt":0.1974521629490948,"score_spread":0.1061748299675568,"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."}}