{"id":"W3193875697","doi":"10.1145/3462329","title":"A Quality-assured Approximate Hardware Accelerators–based on Machine Learning and Dynamic Partial Reconfiguration","year":2021,"lang":"en","type":"article","venue":"ACM Journal on Emerging Technologies in Computing Systems","topic":"Low-power high-performance VLSI design","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Control reconfiguration; Computer science; Field-programmable gate array; Efficient energy use; Reconfigurable computing; Resilience (materials science); Embedded system; Energy consumption; Computer engineering","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":[0.0002201023,0.0003070292,0.0003529966,0.0003189657,0.0001971288,0.0005756637,0.0008132588,0.00028316,0.001844571],"category_scores_gemma":[0.0007999182,0.0001646572,0.0002499312,0.0003403467,0.0002614961,0.0005823091,0.0003793431,0.0004058074,0.0004163312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002872241,"about_ca_system_score_gemma":0.0004846769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007693417,"about_ca_topic_score_gemma":0.000898404,"domain_scores_codex":[0.9997388,0.00003383428,0.00002004399,0.00004392379,0.0001367107,0.00002671414],"domain_scores_gemma":[0.9997385,0.00004852581,0.00005977663,0.00007366893,0.00006157201,0.00001787147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008642456,0.0001206787,0.002878794,0.0004666025,0.0001021547,0.0004403111,0.0002098057,0.2384716,0.1886605,0.03048408,0.006510955,0.5307903],"study_design_scores_gemma":[0.00004647733,0.0005161046,0.0009946952,0.0000347192,0.00003572715,0.0004384817,0.00002411709,0.935156,0.04241723,0.003104934,0.01720032,0.00003117869],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06054467,0.0009011846,0.9297777,0.0001967277,0.0001406274,0.00008663455,0.00007973435,0.002419779,0.005852971],"genre_scores_gemma":[0.7942281,0.0003498123,0.2015187,0.00014811,0.00004484543,0.0000770581,0.0001355666,0.00007366412,0.003424184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001844571,"threshold_uncertainty_score":0.00617075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01942659358015226,"score_gpt":0.2765900885137185,"score_spread":0.2571634949335662,"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."}}