{"id":"W2891927334","doi":"10.48550/arxiv.1810.10999","title":"Reversible Recurrent Neural Networks","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Computer science; Sequence (biology); Forgetting; Encoder; Path (computing); Decoding methods; Artificial intelligence; Artificial neural network; Backpropagation; Flexibility (engineering); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005001759,0.0008952551,0.0008131745,0.0005186741,0.0003589763,0.0009279422,0.001922845,0.0009773481,0.005985823],"category_scores_gemma":[0.002762368,0.0004572653,0.0008969372,0.0006478985,0.0006062733,0.001763599,0.0009262405,0.00129506,0.002217417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008128448,"about_ca_system_score_gemma":0.0008614936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004445167,"about_ca_topic_score_gemma":0.006439652,"domain_scores_codex":[0.9995039,0.0000954959,0.00003146911,0.0001410068,0.0001645161,0.00006363577],"domain_scores_gemma":[0.9992791,0.0002548973,0.00009157366,0.0001894122,0.0001545426,0.00003047076],"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":[0.0001789927,0.00007372304,0.001029241,0.0004286447,0.0001935374,0.0003815031,0.0001150116,0.5322154,0.02839082,0.08249307,0.01093874,0.3435614],"study_design_scores_gemma":[0.00001002488,0.00003519169,0.0001942711,0.00001956072,0.00002776442,0.00011004,0.00001167236,0.9605305,0.009485489,0.02317632,0.006377723,0.00002143356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0146641,0.001147224,0.9695285,0.0003221388,0.0002079242,0.0000650877,0.0004381217,0.003771011,0.009855825],"genre_scores_gemma":[0.5903782,0.002158923,0.3757424,0.0005645751,0.0002837587,0.0002163489,0.002118946,0.0006939864,0.02784295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005985823,"threshold_uncertainty_score":0.0200246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05761062443858757,"score_gpt":0.1886827479784816,"score_spread":0.1310721235398941,"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."}}