{"id":"W4310064233","doi":"10.1016/j.neunet.2022.11.028","title":"SGORNN: Combining scalar gates and orthogonal constraints in recurrent networks","year":2022,"lang":"en","type":"article","venue":"Neural Networks","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Horizon 2020; Natural Sciences and Engineering Research Council of Canada; Narodowe Centrum Nauki","keywords":"Recurrent neural network; Overfitting; Scalar (mathematics); Computer science; Treebank; Probabilistic logic; Algorithm; Artificial intelligence; Context (archaeology); Deep learning; Backpropagation; Artificial neural network; Pattern recognition (psychology); Mathematics; Annotation","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002294188,0.001132221,0.001129548,0.0006065203,0.0003342343,0.001265271,0.001736112,0.0009815665,0.005082559],"category_scores_gemma":[0.005197607,0.0006325268,0.0008137562,0.0008659996,0.0004724105,0.002767409,0.001864188,0.001903686,0.002085684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000524977,"about_ca_system_score_gemma":0.00127465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005299104,"about_ca_topic_score_gemma":0.01318149,"domain_scores_codex":[0.9992332,0.0002900048,0.00007201565,0.0001778435,0.0001441794,0.00008275128],"domain_scores_gemma":[0.9987249,0.0006364068,0.00006997561,0.000245827,0.0002422375,0.00008055034],"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":[0.000552374,0.0002964218,0.00115823,0.0003230937,0.0002458989,0.0001661953,0.0001390495,0.2647437,0.0149996,0.02844024,0.01921427,0.6697209],"study_design_scores_gemma":[0.00002351235,0.0000354859,0.00007110415,0.000008745664,0.00001857024,0.00001214118,0.000006540792,0.9871544,0.002589303,0.008651432,0.00141976,0.000008992432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01195719,0.0002459578,0.9782304,0.0001678328,0.0001294168,0.00008095718,0.0004908431,0.007186206,0.001511315],"genre_scores_gemma":[0.2959864,0.0003834929,0.6909811,0.0004215449,0.0001658086,0.000338186,0.003197635,0.001848185,0.006677644],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005299104,"threshold_uncertainty_score":0.01700282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01793403223735531,"score_gpt":0.2324914549739667,"score_spread":0.2145574227366114,"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."}}