{"id":"W2790071460","doi":"10.1007/s11265-018-1332-4","title":"A Rank Decomposed Statistical Error Compensation Technique for Robust Convolutional Neural Networks in the Near Threshold Voltage Regime","year":2018,"lang":"en","type":"article","venue":"Journal of Signal Processing Systems","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research; Semiconductor Research Corporation","keywords":"MNIST database; Computer science; Convolutional neural network; Redundancy (engineering); Estimator; Pattern recognition (psychology); Compensation (psychology); Artificial intelligence; Algorithm; Artificial neural network; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009439763,0.0009390904,0.0006155015,0.000498625,0.000328516,0.0006554561,0.0008856218,0.0008528108,0.002504873],"category_scores_gemma":[0.00251977,0.0003492541,0.000509017,0.0004593149,0.0004071686,0.001068653,0.0007678936,0.001097688,0.0008005991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004159789,"about_ca_system_score_gemma":0.0009191026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002946837,"about_ca_topic_score_gemma":0.006459599,"domain_scores_codex":[0.9995173,0.00009358564,0.000037151,0.00007448849,0.0002340191,0.0000434432],"domain_scores_gemma":[0.9991804,0.000242143,0.0000964893,0.0001525176,0.0002973721,0.00003099936],"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":[0.0004461089,0.0001363829,0.0006982189,0.0001870857,0.0001280449,0.0001640771,0.00009331086,0.2686598,0.1480882,0.02842779,0.004167083,0.5488038],"study_design_scores_gemma":[0.0000049321,0.00004368167,0.0001580467,0.000006084728,0.000009864994,0.00004390515,0.000005352611,0.9820827,0.01487128,0.00200781,0.0007560459,0.00001027418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007026165,0.0001935984,0.9916779,0.0000770187,0.00004321367,0.00001527237,0.00003198512,0.0003762929,0.0005585866],"genre_scores_gemma":[0.2587848,0.0003994731,0.7324761,0.0001287151,0.000110464,0.00006488114,0.0002875116,0.0002498601,0.007498132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002946837,"threshold_uncertainty_score":0.008379698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0358262283067966,"score_gpt":0.2798921470510717,"score_spread":0.2440659187442751,"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."}}