{"id":"W3166670648","doi":"10.1109/fccm51124.2021.00011","title":"Flexible Instrumentation for Live On-Chip Debug of Machine Learning Training on FPGAs","year":2021,"lang":"en","type":"article","venue":"","topic":"Advancements in Semiconductor Devices and Circuit Design","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council","keywords":"Instrumentation (computer programming); Debugging; Computer science; Embedded system; Firmware; Field-programmable gate array; Key (lock); Computer architecture; Computer hardware; Machine learning; Operating system","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":[0.001170302,0.0008634729,0.0004914131,0.0008929257,0.0003519345,0.0008848917,0.002065007,0.0005938689,0.007089115],"category_scores_gemma":[0.00643769,0.0004475954,0.0002132081,0.0004411936,0.0007899107,0.001560894,0.001682646,0.001195895,0.0009587023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006135497,"about_ca_system_score_gemma":0.0006259484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005370962,"about_ca_topic_score_gemma":0.0007985838,"domain_scores_codex":[0.9989692,0.0002660566,0.00007078442,0.0002079226,0.0003133903,0.0001726177],"domain_scores_gemma":[0.9964021,0.001644095,0.0002808518,0.001222431,0.0003005555,0.0001500171],"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":[0.00252294,0.0005094411,0.02553326,0.0008513719,0.0001424676,0.001518377,0.001930085,0.07609316,0.1536471,0.03574452,0.03100496,0.6705024],"study_design_scores_gemma":[0.000330316,0.00159217,0.01195693,0.0003109704,0.0001017088,0.001327216,0.0005038948,0.4567559,0.408356,0.02170357,0.09688704,0.0001742071],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1662198,0.0008770003,0.7833511,0.0006676246,0.0003541927,0.000279189,0.0006734697,0.03952063,0.008056961],"genre_scores_gemma":[0.8795543,0.0002177625,0.1148668,0.0004058288,0.00004994682,0.0002465839,0.0003713334,0.001126503,0.003161088],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007089115,"threshold_uncertainty_score":0.02371544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05122883513003532,"score_gpt":0.2762047838202545,"score_spread":0.2249759486902192,"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."}}