{"id":"W2771070736","doi":"10.15353/vsnl.v3i1.161","title":"Polyploidism in Deep Neural Networks: m-Parent Evolutionary Synthesis of Deep Neural Networks in Varying Population Sizes","year":2017,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Nvidia","keywords":"MNIST database; Artificial neural network; Artificial intelligence; Modern evolutionary synthesis; Population; Deep neural networks; Computer science; Evolutionary algorithm; Evolutionary acquisition of neural topologies; Biology; Evolutionary biology; Time delay neural network; Demography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063551,0.0001584121,0.0003644321,0.0003404506,0.0003119951,0.0002556577,0.0005225684,0.0000504028,0.000001705018],"category_scores_gemma":[0.00009696565,0.0001413537,0.00009558389,0.0002267995,0.00007469847,0.001402563,0.0001591145,0.0002441471,3.155209e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009959804,"about_ca_system_score_gemma":0.00002664024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002476569,"about_ca_topic_score_gemma":0.00001138166,"domain_scores_codex":[0.9979992,0.0001832834,0.0009579832,0.0002127352,0.0004290555,0.0002177717],"domain_scores_gemma":[0.9979796,0.0004766569,0.0009795518,0.0002304287,0.000236031,0.00009767139],"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":[0.00001750986,0.00008645172,0.06908488,0.0000165887,0.000008887358,0.00001306233,0.0001051927,0.8954886,0.000009903843,0.002219447,0.00002406371,0.03292543],"study_design_scores_gemma":[0.0003077553,0.00002211533,0.4025641,0.000120092,0.000004695331,0.0001375273,0.00005000978,0.5955799,4.033031e-7,0.001128718,0.000005762902,0.00007887816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1555859,0.004369574,0.8373138,0.001707172,0.0007776889,0.0001864716,0.000001993623,0.00001655662,0.00004080653],"genre_scores_gemma":[0.9918832,0.0000439999,0.007794611,0.00004096982,0.0002121668,0.000008122878,0.000005144848,0.000009370071,0.000002385786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8362973,"threshold_uncertainty_score":0.5764236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01165955911402931,"score_gpt":0.2742531588624055,"score_spread":0.2625935997483762,"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."}}