{"id":"W4407829771","doi":"10.1109/mdat.2025.3544537","title":"Understanding Error Propagation in Deep-Learning Neural Networks’ Accelerators and Applications","year":2025,"lang":"en","type":"article","venue":"IEEE Design and Test","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Deep learning; Artificial neural network; Artificial intelligence; Backpropagation; Deep neural networks; Machine learning","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":[0.0001432841,0.00008553357,0.00008515696,0.00008555777,0.0002506193,0.000194022,0.0001420464,0.00004130677,6.748282e-7],"category_scores_gemma":[0.00001254923,0.00008086977,0.00001067104,0.0005740336,0.00004163805,0.0002035204,0.0000443904,0.0001484799,7.551708e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002903034,"about_ca_system_score_gemma":0.00001300549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005021899,"about_ca_topic_score_gemma":0.00001079338,"domain_scores_codex":[0.9993529,0.00004387464,0.0001348268,0.0002619237,0.00005100714,0.0001554176],"domain_scores_gemma":[0.9993613,0.0004076973,0.00004196323,0.0001257328,0.00001707403,0.00004621381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000162842,0.0002004867,0.04698897,0.00006715358,0.00002148659,0.00001270356,0.0004746265,0.1839174,0.004074834,0.5352517,0.001003352,0.227971],"study_design_scores_gemma":[0.0001792985,0.00002408058,0.003312267,0.00001618582,0.000004014265,0.00000407541,0.00002818012,0.9896435,0.0001139891,0.00627295,0.0003121682,0.0000892778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004441923,0.000219044,0.9938984,0.0006974054,0.00004427278,0.000407082,1.545469e-7,0.00008208383,0.0002096413],"genre_scores_gemma":[0.9963063,0.00007224867,0.003187406,0.0002152708,0.00003664758,0.0001331436,0.00000118194,0.000004439699,0.00004333422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9918644,"threshold_uncertainty_score":0.3297774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06211950306999332,"score_gpt":0.2695032183821018,"score_spread":0.2073837153121085,"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."}}