{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002759538,0.0009031675,0.0009223524,0.000520264,0.0005171946,0.001312658,0.001061256,0.001560342,0.004278643],"category_scores_gemma":[0.008263176,0.0008344702,0.0007502288,0.0005711782,0.001406415,0.002660129,0.001398063,0.00270534,0.0008008376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007711852,"about_ca_system_score_gemma":0.001238351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00112526,"about_ca_topic_score_gemma":0.002271451,"domain_scores_codex":[0.9987764,0.0005384221,0.00003868964,0.0001507913,0.0003948722,0.000100912],"domain_scores_gemma":[0.9978815,0.001428162,0.0001244461,0.0003180237,0.0001864723,0.00006138734],"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":[0.0001317629,0.00009915118,0.0007514879,0.0001573667,0.00008010524,0.0001148316,0.00009590726,0.7915977,0.004182917,0.1261765,0.003315739,0.07329648],"study_design_scores_gemma":[0.00003638156,0.00006380975,0.0001326067,0.0000335825,0.00001764659,0.0000495809,0.0000182177,0.8868526,0.001322857,0.1063373,0.005121708,0.0000136924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01096977,0.0007373419,0.98002,0.001217564,0.00004646926,0.00003032085,0.00002614898,0.0002331932,0.006719109],"genre_scores_gemma":[0.4137419,0.0007860223,0.5786877,0.0009314185,0.00008723142,0.0002322916,0.00008334643,0.000286606,0.005163527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004278643,"threshold_uncertainty_score":0.01459396,"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."}}