{"id":"W2963188574","doi":"10.1049/el.2019.1719","title":"GenSynth: a generative synthesis approach to learning generative machines for generate efficient neural networks","year":2019,"lang":"en","type":"article","venue":"Electronics Letters","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Regional Municipality of Waterloo; Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Artificial neural network; Generative grammar; Machine learning; Generator (circuit theory); Computer engineering","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"],"consensus_categories":[],"category_scores_codex":[0.000293065,0.000391015,0.0003676003,0.0001466738,0.0004680082,0.0002189371,0.0009661155,0.00008098351,0.00000382612],"category_scores_gemma":[0.00005726597,0.0003691682,0.0001649875,0.000770663,0.0000382526,0.0002004951,0.0002369868,0.0004573939,0.00003338323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002624682,"about_ca_system_score_gemma":0.00005061896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003889765,"about_ca_topic_score_gemma":0.000003823136,"domain_scores_codex":[0.9970258,0.0002016919,0.0003395556,0.001104687,0.0002812816,0.001046968],"domain_scores_gemma":[0.998448,0.0004327046,0.0001781811,0.0006840692,0.00008210867,0.0001749391],"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":[0.00001910136,0.00004047375,0.00002414791,0.00000479405,0.000039632,6.609951e-7,0.0002193813,0.9136346,0.06128366,0.01568188,0.001575313,0.007476339],"study_design_scores_gemma":[0.0002214389,0.0001147849,0.00002616833,0.000005083578,0.00001586553,0.00001271337,0.000007098349,0.9810382,0.0130354,0.0001479949,0.004937807,0.0004374258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1084754,0.0004247809,0.8844579,0.004608444,0.0002698203,0.001313104,0.000003747041,0.0002382514,0.0002085646],"genre_scores_gemma":[0.6935632,0.0000246124,0.2944473,0.009503672,0.0006370823,0.001435748,0.00003318542,0.0000824161,0.0002727565],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5900105,"threshold_uncertainty_score":0.999876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01115322495863479,"score_gpt":0.2343316133131257,"score_spread":0.2231783883544909,"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."}}