{"id":"W2898902424","doi":"","title":"EcoRNN: Efficient Computing of LSTM RNN on GPUs","year":2018,"lang":"en","type":"article","venue":"International Symposium on Microarchitecture","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Recurrent neural network; Parallel computing; Artificial intelligence; Artificial neural network","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":[0.0003301461,0.0008569444,0.0004752645,0.0004913725,0.0004677835,0.0009060653,0.001660486,0.0005760597,0.0121281],"category_scores_gemma":[0.001500236,0.0004292431,0.0004295562,0.0007439258,0.000262509,0.001151946,0.0007809291,0.0008260262,0.002383512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008394155,"about_ca_system_score_gemma":0.001322334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01324622,"about_ca_topic_score_gemma":0.0333099,"domain_scores_codex":[0.9997702,0.00003423406,0.00001579972,0.00006324972,0.00006822672,0.00004827343],"domain_scores_gemma":[0.9996295,0.00009034965,0.00001730132,0.00007835188,0.0001441951,0.00004033271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001453481,0.0002370721,0.004264928,0.0006377297,0.0003031484,0.0005538575,0.0002851019,0.22567,0.05419631,0.01637151,0.08234289,0.6136839],"study_design_scores_gemma":[0.00006591736,0.00007029338,0.0005360633,0.00001560876,0.00002405572,0.00004319801,0.00003716738,0.9733218,0.01444209,0.003472422,0.007955164,0.00001625467],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.166997,0.002030599,0.7536202,0.0006906659,0.001009106,0.0002099107,0.002146091,0.04611004,0.02718633],"genre_scores_gemma":[0.5156116,0.0004284034,0.4622155,0.0003610859,0.0001313699,0.0002308934,0.002966946,0.002050038,0.01600417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01324622,"threshold_uncertainty_score":0.04057246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007741681398862896,"score_gpt":0.2530854997087013,"score_spread":0.2453438183098384,"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."}}