{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00105654,0.0001576433,0.0002974339,0.00008639783,0.0002372973,0.000140355,0.0002331378,0.00008772011,0.000004078736],"category_scores_gemma":[0.00003784363,0.0001146475,0.00006278967,0.0002051122,0.0001133164,0.0003052534,0.00001188536,0.0004354746,7.378628e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008094037,"about_ca_system_score_gemma":0.00004959296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000015391,"about_ca_topic_score_gemma":0.000002028151,"domain_scores_codex":[0.9986774,0.00007195964,0.000595126,0.0001206037,0.0002639434,0.0002709724],"domain_scores_gemma":[0.999001,0.0003420683,0.0002816988,0.0000761983,0.000241095,0.00005798303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001966452,0.0000255566,0.0001526147,0.0002306622,0.00001527177,0.00003342137,0.0002527458,0.9814939,0.01527075,0.0002547851,0.0005654602,0.001508191],"study_design_scores_gemma":[0.0006310184,0.000232195,0.0002525388,0.0004237497,0.00001971068,0.0005093093,0.0001619988,0.9965794,0.0005715943,0.0002668478,0.0002169686,0.000134688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04889287,0.0007063632,0.9494688,0.00005447779,0.0003684516,0.0004116193,0.000004068713,0.00003828558,0.00005507969],"genre_scores_gemma":[0.9927543,0.000001768622,0.00610755,0.00006004107,0.001022476,0.00001726199,0.000004403669,0.00002571687,0.000006511735],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9438614,"threshold_uncertainty_score":0.4675189,"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."}}