{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001084051,0.001785168,0.001261451,0.001593226,0.0003251056,0.001237884,0.001871703,0.00179014,0.004164282],"category_scores_gemma":[0.002215489,0.0006731456,0.0005621344,0.002997185,0.0009598566,0.003174149,0.0009091941,0.002299162,0.004297265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001213591,"about_ca_system_score_gemma":0.00148282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003752737,"about_ca_topic_score_gemma":0.003781911,"domain_scores_codex":[0.9996365,0.00007819977,0.000044732,0.00008305521,0.000137166,0.00002033191],"domain_scores_gemma":[0.9992249,0.000458001,0.00004415588,0.00003886707,0.0002080187,0.0000260967],"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":[0.00005015347,0.00006075652,0.0002338606,0.007987052,0.00008391959,0.0001008949,0.00006996301,0.006911004,0.000925248,0.04988674,0.03457503,0.8991153],"study_design_scores_gemma":[0.00001176619,0.0000954441,0.0003272871,0.003172502,0.00007776003,0.0004149273,0.00004348875,0.006554793,0.001149244,0.03746698,0.9506322,0.00005357289],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002592209,0.9758955,0.01576024,0.001022932,0.0007476653,0.00001825184,0.0000716243,0.0001033684,0.006121332],"genre_scores_gemma":[0.003554427,0.982219,0.009339148,0.000612887,0.0008015294,0.00003938811,0.0001290898,0.00003920571,0.003265367],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.004164282,"threshold_uncertainty_score":0.01393092,"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."}}