{"id":"W2952800213","doi":"10.48550/arxiv.1811.10396","title":"Learning to Skip Ineffectual Recurrent Computations in LSTMs","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Computation; Pruning; Inference; Set (abstract data type); Recurrent neural network; Process (computing); Speedup; Computer engineering; Parallel computing; Artificial intelligence; Algorithm; Artificial neural network; Programming language","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":[0.0006159727,0.001006626,0.00071964,0.0003480967,0.0003401358,0.0006894417,0.001263999,0.0006596153,0.002420129],"category_scores_gemma":[0.003621771,0.0005153037,0.0004698179,0.0003957032,0.0005496062,0.001880701,0.0009289246,0.001390879,0.0006637216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005647102,"about_ca_system_score_gemma":0.000886926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002163518,"about_ca_topic_score_gemma":0.006192919,"domain_scores_codex":[0.9996655,0.00005654884,0.00002895916,0.00009318216,0.00009420946,0.00006156158],"domain_scores_gemma":[0.9992183,0.0003919422,0.00009752162,0.0001258892,0.0001278774,0.00003831401],"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":[0.0004496422,0.0002265526,0.002198432,0.0004312344,0.0001799312,0.0005408731,0.0002749395,0.4880027,0.07826074,0.02655751,0.007014954,0.3958625],"study_design_scores_gemma":[0.000009903189,0.00003660491,0.0001415959,0.000009326674,0.00001443142,0.00004055373,0.0000113374,0.9817418,0.01060968,0.006742401,0.0006359421,0.000006333702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08977878,0.0004239649,0.9039822,0.0002652685,0.0001460261,0.0000551841,0.0001619073,0.002926016,0.002260815],"genre_scores_gemma":[0.7680049,0.0003159886,0.2271938,0.0002608022,0.00007439875,0.0001216638,0.0004392843,0.0002863413,0.003302757],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002420129,"threshold_uncertainty_score":0.008096159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0630774526983908,"score_gpt":0.2118791832265717,"score_spread":0.1488017305281809,"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."}}