{"id":"W3078478003","doi":"10.1109/tcds.2020.3017100","title":"Accurate and Fast Deep Evolutionary Networks Structured Representation Through Activating and Freezing Dense Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Cognitive and Developmental Systems","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Variety (cybernetics); Convergence (economics); Construct (python library); Artificial neural network; Training (meteorology); Artificial intelligence; Deep learning; Representation (politics); Point (geometry); Evolutionary algorithm; Computer network","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":[],"consensus_categories":[],"category_scores_codex":[0.00007293509,0.0001999009,0.0001895853,0.00004808191,0.0007840804,0.0001944977,0.00009657469,0.00009359583,0.000004652953],"category_scores_gemma":[0.000008621732,0.0001994132,0.00002744847,0.0003823857,0.0001012433,0.0007841171,0.0000168617,0.0002290503,0.000002995276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004344477,"about_ca_system_score_gemma":0.00003481919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008996112,"about_ca_topic_score_gemma":0.00001591783,"domain_scores_codex":[0.9986883,0.00008865261,0.0002867314,0.0005441141,0.0001698686,0.000222288],"domain_scores_gemma":[0.9992867,0.00028711,0.0001050873,0.00007689798,0.00009157423,0.0001526049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005090045,0.0004061389,0.005068691,0.0003585179,0.001103133,0.0001120038,0.02878582,0.2191656,0.00542996,0.006553678,0.0006609579,0.7318465],"study_design_scores_gemma":[0.0008021023,0.00008506449,0.006391659,0.000136988,0.00002335339,0.0002159503,0.00355958,0.9875917,0.0005992979,0.000153945,0.0001078447,0.0003324857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03756777,0.0008229167,0.9604358,0.0002493252,0.0001923754,0.0004460896,0.00001797983,0.0001044354,0.0001633316],"genre_scores_gemma":[0.987686,0.000403845,0.01137049,0.0002829669,0.00009470264,0.0001100605,0.00001440246,0.00001278525,0.00002469103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9501183,"threshold_uncertainty_score":0.8131835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02730468067724522,"score_gpt":0.2512561656906926,"score_spread":0.2239514850134474,"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."}}