{"id":"W4414240964","doi":"10.54254/2753-8818/2025.dl26846","title":"From RNNs to BERT: A Review of Neural Models for Sequence Learning","year":2025,"lang":"en","type":"review","venue":"Theoretical and Natural Science","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Transformer; Sequence learning; Artificial neural network; Language model; Sequence (biology); Process (computing)","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":[],"consensus_categories":[],"category_scores_codex":[0.0006000188,0.000239102,0.0008336355,0.00009783146,0.0002273736,0.0001032115,0.001855287,0.00006998597,0.000007119022],"category_scores_gemma":[0.0003485461,0.000152243,0.0001960836,0.001594609,0.0007452254,0.0002579252,0.0008165463,0.0003362493,0.000003100661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000288982,"about_ca_system_score_gemma":0.0002481052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000994666,"about_ca_topic_score_gemma":3.71669e-7,"domain_scores_codex":[0.9980422,0.00008160229,0.0004216989,0.0007607124,0.0003235931,0.0003701526],"domain_scores_gemma":[0.9980558,0.0009891936,0.0001500308,0.0004563809,0.0001549566,0.0001936349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[6.489286e-7,0.000003577967,1.324e-8,0.002926375,0.000001966896,3.091659e-7,0.000009032875,0.000003517884,0.000003889122,0.4248574,0.0000582851,0.572135],"study_design_scores_gemma":[0.000124478,0.0001900816,0.000001194948,0.1274358,0.0002810736,0.00002779102,0.000003045765,0.1770745,0.00002787092,0.3089035,0.3850978,0.0008328863],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003610416,0.9623228,0.03487452,0.001295845,0.0001724745,0.0008935506,0.00002918307,0.00004468061,0.0003632965],"genre_scores_gemma":[0.001085136,0.9878435,0.01006707,0.0006976447,0.00006734808,0.0001190804,0.000009786974,0.000005630369,0.0001048332],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5713021,"threshold_uncertainty_score":0.6208289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0282848952368717,"score_gpt":0.3532016361497523,"score_spread":0.3249167409128805,"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."}}