{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004687706,0.00016147,0.0002072934,0.00008089576,0.0002530112,0.0001171261,0.0005305481,0.00005653932,0.00002844249],"category_scores_gemma":[0.0000145132,0.0001713228,0.000045581,0.0003779606,0.00008273412,0.0001985184,0.0008630745,0.0007679079,6.280285e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004456529,"about_ca_system_score_gemma":0.00002306767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009288278,"about_ca_topic_score_gemma":0.00001949394,"domain_scores_codex":[0.9982541,0.0002064926,0.0003158989,0.0005011194,0.0002494164,0.0004729492],"domain_scores_gemma":[0.9992992,0.0001750169,0.00008968616,0.0003019145,0.00001982603,0.0001143792],"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":[0.00001202615,0.00003558877,0.01919298,0.000003641051,0.000005693912,0.00008562511,0.0001968389,0.7359444,0.000003703102,0.0109002,0.0002622922,0.233357],"study_design_scores_gemma":[0.0004131777,0.00007929049,0.005086246,0.00001800356,0.000002559474,0.00009250578,0.00004013551,0.9930546,8.056689e-7,0.0007446794,0.00029279,0.0001752221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5092279,0.003678992,0.4812278,0.001661482,0.002988653,0.0004052441,0.000002312859,0.000242475,0.0005651734],"genre_scores_gemma":[0.99712,0.00004200552,0.001864191,0.0007654881,0.0001398618,0.00003367283,0.000007333711,0.00001080303,0.00001670475],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4878921,"threshold_uncertainty_score":0.6986339,"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."}}