{"id":"W2742479298","doi":"10.1109/islped.2017.8009208","title":"A case for efficient accelerator design space exploration via Bayesian optimization","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayesian optimization; Computer science; Design space exploration; Artificial intelligence; Artificial neural network; Machine learning; Hardware acceleration; Bayesian probability; Space (punctuation); Bayesian network; Deep learning; Computer engineering; Embedded system; Field-programmable gate array","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":[],"consensus_categories":[],"category_scores_codex":[0.0002886604,0.0001806247,0.0001520266,0.0001128587,0.00105944,0.0007016734,0.0005879732,0.00007115251,0.00002263464],"category_scores_gemma":[0.0002678995,0.0001718985,0.00005354567,0.0001505964,0.00004783217,0.001948397,0.0001686812,0.0000606344,0.00001484488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001026899,"about_ca_system_score_gemma":0.00007207861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001418802,"about_ca_topic_score_gemma":0.000006940756,"domain_scores_codex":[0.9987482,0.00005935078,0.000222277,0.0005207171,0.0001803518,0.0002690746],"domain_scores_gemma":[0.9981532,0.0001086318,0.0002722658,0.000906877,0.0004322667,0.000126742],"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":[0.00001205182,0.00006259829,0.000002665842,0.000004383945,0.000007205251,0.00005358324,0.0003372088,0.9835197,0.0001377499,0.004236437,0.0001030607,0.01152336],"study_design_scores_gemma":[0.000807334,0.00008523645,0.000004495467,0.000005457231,0.000005849035,0.0001353985,0.00004718423,0.9904501,0.007606162,0.00055404,0.00007450641,0.0002241949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002146149,0.000007422683,0.9969018,0.0008878205,0.0004168309,0.001087774,0.000002768617,0.0002540966,0.0004200037],"genre_scores_gemma":[0.1105844,0.000004123464,0.8886749,0.0001007573,0.00006822739,0.0001921252,0.000004468744,0.0000212535,0.0003497629],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1105629,"threshold_uncertainty_score":0.8148465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05832393744523108,"score_gpt":0.3059853220786162,"score_spread":0.2476613846333852,"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."}}