{"id":"W2891926718","doi":"10.48550/arxiv.1709.02043","title":"The Mating Rituals of Deep Neural Networks: Learning Compact Feature\\n Representations through Sexual Evolutionary Synthesis","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"MNIST database; Artificial intelligence; Modern evolutionary synthesis; Computer science; Artificial neural network; Evolutionary algorithm; Feature (linguistics); Mating; Evolutionary programming; Machine learning; Biology; Evolutionary biology; Ecology","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0005236904,0.0003715892,0.0004963444,0.00009390028,0.001818277,0.0004044044,0.002586295,0.0002520809,0.00001512345],"category_scores_gemma":[0.0006182025,0.0003347729,0.0003031703,0.0003287401,0.0004244779,0.0008608621,0.001775505,0.0008915932,0.000008614326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001215355,"about_ca_system_score_gemma":0.00009735121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005726427,"about_ca_topic_score_gemma":0.0001009941,"domain_scores_codex":[0.9972189,0.0008256884,0.0003242459,0.0009611544,0.0001821912,0.0004878045],"domain_scores_gemma":[0.9952944,0.001604506,0.0009573794,0.001711977,0.0003234582,0.0001082658],"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":[0.00002242961,0.00003717098,0.002640126,0.0000219852,0.0001984115,0.0000401053,0.0003049691,0.9849148,0.00002281161,0.00758223,0.0009191913,0.003295765],"study_design_scores_gemma":[0.0001544294,0.00003365881,0.00428315,0.00006829853,0.0001128796,0.000006106814,0.0004919539,0.9893743,0.00007988958,0.004818123,0.0002500665,0.0003270917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01156561,0.0007312162,0.9827957,0.000682214,0.0008649293,0.0003318423,0.00001231679,0.0001353832,0.002880768],"genre_scores_gemma":[0.9935023,0.0002591635,0.004894024,0.0000267992,0.0002887309,0.000002352334,0.00001395421,0.00002220981,0.0009904361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9819368,"threshold_uncertainty_score":0.9999104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06496836358718759,"score_gpt":0.2262828118840555,"score_spread":0.1613144482968679,"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."}}