{"id":"W2946208315","doi":"10.23919/date.2019.8714957","title":"Using Machine Learning for Quality Configurable Approximate Computing","year":2019,"lang":"en","type":"article","venue":"","topic":"Low-power high-performance VLSI design","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Flexibility (engineering); Overhead (engineering); Rollback; Computation; Quality (philosophy); Key (lock); Approximation error; Approximation algorithm; Error detection and correction; Control (management); Computer engineering; Machine learning; Artificial intelligence; Algorithm; Database","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":[0.0005450505,0.0001833089,0.0002778494,0.00007679696,0.0001064229,0.00006338814,0.0001402993,0.00007656729,0.000220706],"category_scores_gemma":[0.00002182534,0.0001732724,0.00006656115,0.0001421794,0.00001427708,0.000221512,0.00002721737,0.0001984778,0.0001298387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007834468,"about_ca_system_score_gemma":0.00001399011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007593365,"about_ca_topic_score_gemma":0.000004159858,"domain_scores_codex":[0.9988958,0.00002798721,0.0003122875,0.0002055301,0.0001387628,0.0004196797],"domain_scores_gemma":[0.9995059,0.0001299681,0.0000509758,0.00020866,0.00004601311,0.0000584727],"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":[0.00001963399,0.0000167683,0.0148034,0.000663542,0.00006684462,7.745354e-7,0.0003696375,0.8244435,0.15497,0.00266777,0.00014654,0.001831554],"study_design_scores_gemma":[0.0006190084,0.00002753316,0.0003039607,0.00003200708,0.000008753308,0.000003728002,0.00007847614,0.9599317,0.03593252,0.00004748217,0.002749441,0.0002654191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.667021,0.0001203091,0.3186576,0.000009541594,0.0004579728,0.0004191984,0.000003637249,0.0007327033,0.012578],"genre_scores_gemma":[0.9710442,0.000005846799,0.02791019,0.0000372896,0.00006568286,0.00000508341,0.00001807031,0.00006047045,0.0008531493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3040232,"threshold_uncertainty_score":0.7065842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03633054190274105,"score_gpt":0.2765791814586281,"score_spread":0.2402486395558871,"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."}}