{"id":"W2945889381","doi":"10.1007/978-3-030-18305-9_22","title":"Memory-Efficient Backpropagation for Recurrent Neural Networks","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Recurrent neural network; Backpropagation; Flexibility (engineering); Sequence (biology); Artificial neural network; Process (computing); Artificial intelligence; Long short term memory; Dependency (UML); Pattern recognition (psychology); Algorithm","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":[0.0005949591,0.00056956,0.0005146674,0.0004624278,0.0003407788,0.0003696882,0.003187388,0.0002840873,0.00000856538],"category_scores_gemma":[0.00006078726,0.0005302198,0.0001907896,0.0007303894,0.0003900146,0.0003858332,0.001091288,0.00077954,0.00003837837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003817016,"about_ca_system_score_gemma":0.0002827975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001710523,"about_ca_topic_score_gemma":0.00001661653,"domain_scores_codex":[0.9957894,0.0000296606,0.0006160109,0.001980753,0.0007500238,0.0008341558],"domain_scores_gemma":[0.9964,0.0008113285,0.000458326,0.001796962,0.0003545497,0.0001788604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004607481,0.00001273667,0.000001221208,0.00001276937,0.000002320508,0.000002210177,0.00004712451,0.5454504,0.00001381912,0.009936537,0.0000271997,0.444489],"study_design_scores_gemma":[0.0002609814,0.0002035698,0.00002180068,0.0001284144,0.000007517215,0.00002376517,5.549014e-8,0.9629045,0.0003124076,0.03419693,0.001380987,0.00055913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003117291,0.0004831096,0.9920413,0.001079728,0.003628214,0.001875121,0.000007406787,0.0002207735,0.0006331187],"genre_scores_gemma":[0.2399727,0.00008835702,0.7533047,0.00315196,0.002231781,0.0002015467,0.00006271525,0.0001400767,0.0008461634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4439299,"threshold_uncertainty_score":0.9997149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02031566103638063,"score_gpt":0.2632183953868266,"score_spread":0.242902734350446,"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."}}