{"id":"W3161593038","doi":"10.1109/icfpt51103.2020.00057","title":"Towards Overlay-based Rapid In-Circuit Tuning of Deep Learning Designs","year":2020,"lang":"en","type":"article","venue":"","topic":"VLSI and Analog Circuit Testing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council","keywords":"Field-programmable gate array; Computer science; Overlay; Debugging; Datapath; Computer architecture; Embedded system; Deep learning; Profiling (computer programming); Computer hardware; Artificial neural network; Artificial intelligence","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":[0.0003262869,0.0001187999,0.000213758,0.0001058121,0.00006411759,0.00006120341,0.0005872958,0.00004634199,0.00008278601],"category_scores_gemma":[0.000343966,0.0001162053,0.00007222444,0.0007450054,0.00002667168,0.000256114,0.0001000468,0.0002183904,0.00002230539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002400328,"about_ca_system_score_gemma":0.0001053137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006213666,"about_ca_topic_score_gemma":0.000004904733,"domain_scores_codex":[0.9987664,0.00009749897,0.0002847671,0.0003214345,0.0002491403,0.0002807249],"domain_scores_gemma":[0.9993819,0.0001567076,0.0001021752,0.0001837688,0.00005599942,0.0001194462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[7.123297e-7,0.00004490808,0.02734836,0.00007138527,0.00001110426,0.00006339423,0.00271748,0.01880496,0.03058,0.01341197,0.00003011781,0.9069156],"study_design_scores_gemma":[0.0004843994,0.0002017494,0.00786781,0.00005175239,0.000004332214,0.000003846204,0.0001343767,0.981943,0.00826732,0.0004654083,0.0003457995,0.0002301641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009719999,0.00008833411,0.9723372,0.000483014,0.00004198479,0.00006363537,1.716511e-7,0.0002048313,0.01706081],"genre_scores_gemma":[0.9870133,0.000002483235,0.01200089,0.0009196086,0.00003608835,0.000002681081,0.00000102781,0.000008986695,0.00001493817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9772933,"threshold_uncertainty_score":0.4738716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06397177591804296,"score_gpt":0.2469605852393546,"score_spread":0.1829888093213117,"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."}}