{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007313079,0.0003831681,0.000288993,0.0003695274,0.0002356331,0.0005005665,0.0007266488,0.0005685044,0.00141672],"category_scores_gemma":[0.001751932,0.000282918,0.0003970897,0.0002397486,0.000994956,0.0008972505,0.0009080445,0.0007998386,0.0002336434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004968887,"about_ca_system_score_gemma":0.0002612725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006357612,"about_ca_topic_score_gemma":0.001100589,"domain_scores_codex":[0.9998293,0.00005611668,0.000007128695,0.00004133099,0.00004648072,0.00001961655],"domain_scores_gemma":[0.9995866,0.0002145359,0.0000446554,0.0000881544,0.00004376083,0.00002225233],"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":[0.00008547868,0.00006371651,0.001624673,0.00006931523,0.00005945866,0.0001852391,0.0001833959,0.7278474,0.03732829,0.06616197,0.001156623,0.1652345],"study_design_scores_gemma":[0.000006733939,0.00004069871,0.0001499947,0.000007453933,0.000007782907,0.00004510301,0.00001230908,0.981384,0.006063662,0.01111345,0.001163173,0.000005650442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1285767,0.000403017,0.8624825,0.0003283991,0.00006045171,0.00005282053,0.00004736698,0.0004431162,0.007605645],"genre_scores_gemma":[0.8214193,0.000218939,0.1730659,0.0001697735,0.00002644178,0.00008775237,0.00008731845,0.00009334673,0.004831293],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00141672,"threshold_uncertainty_score":0.004739404,"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."}}