{"id":"W3092504998","doi":"10.1109/dac18072.2020.9218728","title":"Late Breaking Results: Building an On-Chip Deep Learning Memory Hierarchy Brick by Brick","year":2020,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Memory footprint; Computer science; Chip; Footprint; Energy consumption; Lossless compression; Memory hierarchy; Embedded system; Data compression; Artificial intelligence; Engineering; Parallel computing; Electrical engineering; Operating system; Geology; Telecommunications","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":[0.0004866809,0.0008126407,0.0004947659,0.0003129987,0.0003943646,0.00113564,0.002472099,0.000648027,0.009935302],"category_scores_gemma":[0.00160814,0.0004049545,0.0005414671,0.0003282808,0.0005067241,0.002336616,0.001064592,0.001960455,0.002789378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009272441,"about_ca_system_score_gemma":0.001605459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005533409,"about_ca_topic_score_gemma":0.01107669,"domain_scores_codex":[0.9996483,0.00004610121,0.00001793826,0.00007291519,0.0001378395,0.000076829],"domain_scores_gemma":[0.9995722,0.00009668303,0.00002375605,0.0001291689,0.0001352997,0.00004299634],"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":[0.0007352955,0.0005847702,0.001896388,0.0005402381,0.0002806511,0.0002926211,0.0001753799,0.1495194,0.06653896,0.04459515,0.05188382,0.6829574],"study_design_scores_gemma":[0.0001141802,0.0006399291,0.0005861091,0.00007133185,0.0001514478,0.0001231536,0.00007345046,0.8523037,0.07674208,0.0321864,0.03696334,0.00004479873],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1145642,0.003415602,0.8293881,0.001853992,0.0007728162,0.0001558349,0.0008766054,0.01409662,0.03487627],"genre_scores_gemma":[0.6009518,0.0009544085,0.3645729,0.001621659,0.000129224,0.0001758708,0.00198215,0.0007804431,0.02883156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009935302,"threshold_uncertainty_score":0.03323686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02047091235889505,"score_gpt":0.2603319045971976,"score_spread":0.2398609922383025,"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."}}