{"id":"W4313016919","doi":"10.1109/ijcnn55064.2022.9892810","title":"E-LSTM: An extension to the LSTM architecture for incorporating long lag dependencies","year":2022,"lang":"en","type":"article","venue":"2022 International Joint Conference on Neural Networks (IJCNN)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Compute Canada","keywords":"Computer science; Extension (predicate logic); Lag; Process (computing); Recurrent neural network; Long short term memory; Architecture; Artificial intelligence; Transmission (telecommunications); Artificial neural network; Pattern recognition (psychology); Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004328204,0.0007101101,0.0003628224,0.0003006806,0.0002470194,0.0005352499,0.001232812,0.0009567245,0.005826331],"category_scores_gemma":[0.001450252,0.0002962405,0.0004603496,0.0004982983,0.0002381917,0.00159508,0.0007280348,0.001176573,0.001485016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003150928,"about_ca_system_score_gemma":0.0007459554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003064497,"about_ca_topic_score_gemma":0.007059559,"domain_scores_codex":[0.9998342,0.00003246481,0.00001557197,0.00004846533,0.00004439762,0.00002492646],"domain_scores_gemma":[0.9997684,0.00008398516,0.00002220604,0.00004009936,0.0000717495,0.00001359548],"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":[0.0003128866,0.0001956438,0.001579271,0.0003768878,0.0002285554,0.0005944939,0.0001778466,0.20352,0.06176454,0.01703327,0.0168246,0.697392],"study_design_scores_gemma":[0.00001577153,0.00006643469,0.0005564278,0.0000293652,0.00003593489,0.0001724342,0.00001774164,0.969815,0.01192009,0.008026388,0.009324448,0.00001993541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01598133,0.0006975806,0.9744,0.0003076332,0.0002337036,0.00007188447,0.0004971264,0.003361627,0.004449038],"genre_scores_gemma":[0.4093825,0.001179333,0.5720125,0.0005240003,0.0001995495,0.0002209973,0.001502996,0.0004216261,0.0145564],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005826331,"threshold_uncertainty_score":0.01949102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04506472041204799,"score_gpt":0.2795477796332216,"score_spread":0.2344830592211737,"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."}}