{"id":"W2032676284","doi":"10.1016/j.neunet.2009.10.009","title":"Temporal-Kernel Recurrent Neural Networks","year":2009,"lang":"en","type":"article","venue":"Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Computer science; Connectionism; Artificial intelligence; Task (project management); String (physics); Kernel (algebra); Term (time); Sequence (biology); Recall; Machine learning; Artificial neural network; Mathematics","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":[0.0002288135,0.0004746245,0.000414696,0.00009031908,0.000442339,0.0004694815,0.001763002,0.0002210409,0.00002841469],"category_scores_gemma":[0.00002020569,0.0004180472,0.0002669551,0.001192895,0.0000802184,0.0007115727,0.0003032184,0.0009056089,0.00002594946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004959974,"about_ca_system_score_gemma":0.00001702221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001530358,"about_ca_topic_score_gemma":0.0000132967,"domain_scores_codex":[0.9967852,0.0001397702,0.0006117405,0.0009853427,0.0003947793,0.001083215],"domain_scores_gemma":[0.9977764,0.0001477354,0.0002570161,0.00124366,0.0001534323,0.0004217351],"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":[0.00001998306,0.0001470056,0.0008373167,0.000002714434,0.0000115853,0.0000432623,0.00003720941,0.4601339,0.00001697657,0.01273397,0.03950899,0.4865071],"study_design_scores_gemma":[0.0003372083,0.0002326705,0.004762655,0.00001828416,0.00001204311,0.00004035514,0.000002894221,0.9823362,0.000009613387,0.001147688,0.01063476,0.0004656033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02791077,0.003198019,0.9451802,0.01299893,0.004997277,0.001128302,0.000004135389,0.00174695,0.002835363],"genre_scores_gemma":[0.9889756,0.0001762723,0.002264818,0.005962461,0.002244021,0.00004524616,0.00003377207,0.00002864939,0.0002691941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9610648,"threshold_uncertainty_score":0.9998271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01770525029920036,"score_gpt":0.2562555405495667,"score_spread":0.2385502902503663,"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."}}