{"id":"W7117501352","doi":"10.1109/tc.2025.3649209","title":"Dual-Pronged Deep Learning Preprocessing on Heterogeneous Platforms With CPU, Accelerator and CSD","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Computers","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Preprocessor; Deep learning; Bottleneck; Data pre-processing; Dram; Central processing unit; Consistency (knowledge bases); Energy consumption","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":[0.0005749289,0.001451101,0.0007051922,0.0008382538,0.0006930201,0.001505843,0.003915549,0.0005574424,0.00737676],"category_scores_gemma":[0.001847044,0.0006354086,0.0006591998,0.001598192,0.0005850769,0.003539132,0.002280301,0.001496291,0.002320379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001245048,"about_ca_system_score_gemma":0.001886203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003398269,"about_ca_topic_score_gemma":0.007499052,"domain_scores_codex":[0.9992631,0.00006983274,0.00006458892,0.0002498747,0.0002021549,0.0001504521],"domain_scores_gemma":[0.9991395,0.0001590336,0.00006189449,0.0003432569,0.0002111798,0.00008497297],"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":[0.001866029,0.0008700361,0.007950806,0.0007046338,0.0002911645,0.0006840617,0.0002443072,0.0707897,0.08066053,0.01584851,0.08040423,0.739686],"study_design_scores_gemma":[0.0003189348,0.0007431634,0.002854994,0.00006404676,0.0001927093,0.0005360253,0.0002444997,0.8309122,0.1124664,0.01293333,0.03862796,0.0001057481],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.205321,0.005085555,0.7370466,0.00150945,0.001111204,0.0003496856,0.001425694,0.0278243,0.02032655],"genre_scores_gemma":[0.7192664,0.0009728656,0.2625446,0.001069363,0.0001801608,0.0003674846,0.002831726,0.0005358104,0.01223154],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00737676,"threshold_uncertainty_score":0.02467769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01618098472712701,"score_gpt":0.2550504608776606,"score_spread":0.2388694761505336,"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."}}