{"id":"W4415014456","doi":"10.1016/j.asoc.2025.114015","title":"Optimizing deep learning predictive models: A comprehensive review of RNN and its variant architectures","year":2025,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hydro-Québec; Université du Québec à Chicoutimi","funders":"Canada Excellence Research Chairs, Government of Canada; Canada Research Chairs","keywords":"Hyperparameter; Deep learning; Artificial neural network; Recurrent neural network; Deep neural networks; Prognostics","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":[0.0002428597,0.0001561209,0.0002995875,0.000123347,0.0002879128,0.00004285785,0.0003958886,0.00005791325,0.000001530479],"category_scores_gemma":[0.00002815889,0.0001550363,0.00006106123,0.0005291724,0.00004657049,0.00005772363,0.0005498708,0.0002841097,0.000001222114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002417543,"about_ca_system_score_gemma":0.00003817989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006943593,"about_ca_topic_score_gemma":2.672963e-7,"domain_scores_codex":[0.9988181,0.00005367411,0.0003589923,0.0004282337,0.0001367716,0.0002042418],"domain_scores_gemma":[0.9990228,0.0003008207,0.0002151066,0.0002691909,0.0001424134,0.00004970596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001372656,0.00006653592,0.00001386419,0.002781483,0.0001159194,0.000003663247,0.002065487,0.2309408,0.002591772,0.4119716,0.00008119189,0.3493539],"study_design_scores_gemma":[0.0001445311,0.0000341888,0.00008325835,0.001120087,0.00002182322,0.00001294975,0.00007123256,0.9832938,0.001521609,0.01297244,0.0005844455,0.0001395723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001780644,0.01130658,0.9819774,0.000181772,0.00003037021,0.0004727929,7.634338e-7,0.0003676283,0.003882048],"genre_scores_gemma":[0.8454631,0.001013658,0.1527572,0.0006833444,0.00001758442,0.00004111962,0.00000166255,0.000008382844,0.00001396882],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8436825,"threshold_uncertainty_score":0.6322196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01320038705001348,"score_gpt":0.253790325492429,"score_spread":0.2405899384424155,"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."}}