{"id":"W3015357480","doi":"10.1101/2020.04.08.031484","title":"Developing a novel recurrent neural network architecture with fewer parameters and good learning performance","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Recurrent neural network; Computer science; Memorization; Artificial intelligence; Task (project management); Deep learning; Machine learning; Architecture; Sequence learning; Core (optical fiber); Artificial neural network; Engineering; Cognitive psychology; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002382298,0.0005440449,0.0004652358,0.00009121726,0.0003965695,0.0005824884,0.000973977,0.0002086421,0.000001080435],"category_scores_gemma":[0.00002973595,0.000489599,0.00007391403,0.0008303275,0.000102224,0.0002057645,0.001224562,0.001509313,0.000006865778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009097946,"about_ca_system_score_gemma":0.0002820393,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008204003,"about_ca_topic_score_gemma":0.000001607752,"domain_scores_codex":[0.9972773,0.00007895094,0.0003716652,0.001283596,0.000339262,0.0006492425],"domain_scores_gemma":[0.9982549,0.00009459873,0.0003766884,0.0008114916,0.0001677208,0.000294612],"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":[0.0002454413,0.0004045894,0.07603822,0.002554154,0.001068372,0.000227691,0.0003551418,0.7779071,0.07173005,0.06537957,0.0008852066,0.003204476],"study_design_scores_gemma":[0.001478682,0.0005653353,0.2452104,0.002647867,0.0001868585,9.840882e-7,0.000004108421,0.7120177,0.0112619,0.00004408435,0.02272272,0.003859318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5822322,0.0004231735,0.413191,0.002497006,0.0004680692,0.000634679,0.000009334553,0.0005401425,0.000004487942],"genre_scores_gemma":[0.8019193,0.0001624552,0.1968961,0.0004969346,0.0003002797,0.0001679219,2.412963e-7,0.000055305,0.000001423756],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2196871,"threshold_uncertainty_score":0.9997556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02164088647278581,"score_gpt":0.2136876193953879,"score_spread":0.1920467329226021,"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."}}