{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002994247,0.001401,0.001278127,0.0006092254,0.0003882541,0.001160343,0.001678774,0.00222343,0.003096258],"category_scores_gemma":[0.01253796,0.0007802664,0.0007778128,0.000470581,0.002627396,0.001725059,0.002885447,0.0030332,0.0005584448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001665182,"about_ca_system_score_gemma":0.001175101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001533422,"about_ca_topic_score_gemma":0.002280834,"domain_scores_codex":[0.9990222,0.0004586141,0.00003403741,0.000213107,0.0001791186,0.00009288441],"domain_scores_gemma":[0.9940502,0.00492343,0.0002987637,0.0003486768,0.0002295135,0.0001493339],"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":[0.00007467197,0.00003285982,0.0006232384,0.00004776956,0.00002797826,0.00005581595,0.00003759483,0.9377666,0.0008257367,0.04410586,0.0009615218,0.01544041],"study_design_scores_gemma":[0.000007085818,0.00001274348,0.00003091686,0.000006551686,0.000002214918,0.000009723025,0.000003094083,0.9816895,0.000318492,0.01774001,0.0001760729,0.000003670826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01410339,0.0002194443,0.9817847,0.0006795466,0.00003662469,0.00003892196,0.00006466546,0.0003372402,0.002735409],"genre_scores_gemma":[0.7354133,0.0003403557,0.2541017,0.0008506492,0.0001341211,0.000346442,0.0003851418,0.0003308954,0.008097392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003096258,"threshold_uncertainty_score":0.01583523,"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."}}