{"id":"W4291141759","doi":"10.1145/3552513","title":"SHARP: An Adaptable, Energy-Efficient Accelerator for Recurrent Neural Networks","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Embedded Computing Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"Agencia Estatal de Investigación; Institució Catalana de Recerca i Estudis Avançats","keywords":"Computer science; Recurrent neural network; Application-specific integrated circuit; Computation; Field-programmable gate array; Scheduling (production processes); Efficient energy use; Hardware acceleration; Parallel computing; Computer engineering; Artificial intelligence; Embedded system; Artificial neural network; 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","sts"],"consensus_categories":[],"category_scores_codex":[0.000454391,0.0003550958,0.0003682752,0.0002257839,0.00216111,0.0002252855,0.002477169,0.00007423932,0.00001277756],"category_scores_gemma":[0.00001207737,0.0003870628,0.0001962974,0.001276809,0.00003569378,0.0002755916,0.0001278733,0.000518989,0.000003762022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002979623,"about_ca_system_score_gemma":0.00006640633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000315719,"about_ca_topic_score_gemma":0.00000715601,"domain_scores_codex":[0.9966419,0.0003345235,0.0006531426,0.001102057,0.0005283047,0.0007400363],"domain_scores_gemma":[0.9968258,0.0005655886,0.0003138733,0.001890956,0.0001569411,0.000246841],"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":[0.00003202768,0.0002875835,0.000001763451,0.000009552901,0.00002440773,0.000002706701,0.0002812464,0.9192144,0.00005827752,0.0104939,0.0002989776,0.06929516],"study_design_scores_gemma":[0.0005381302,0.000514872,0.000009759217,0.00001875015,0.00001829415,0.00006752989,0.0002443394,0.9913431,0.00008076338,0.0002506792,0.00651408,0.0003997159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005162297,0.000303573,0.9887831,0.0003556943,0.003494235,0.0009493696,0.00004515822,0.0008487529,0.00005779857],"genre_scores_gemma":[0.9694047,0.000006043271,0.02857421,0.0004160176,0.0003365581,0.001036439,0.00003815508,0.00005576873,0.0001321217],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9642424,"threshold_uncertainty_score":0.9998581,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03637421211420172,"score_gpt":0.2820211464391624,"score_spread":0.2456469343249607,"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."}}