{"id":"W3008067816","doi":"10.1109/tcsii.2020.2977015","title":"A Novel Architecture for Early Detection of Negative Output Features in Deep Neural Network Accelerators","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits & Systems II Express Briefs","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Computer science; Speedup; Computation; Activation function; Benchmark (surveying); Deep learning; Feature (linguistics); Object detection; Dataflow; Pattern recognition (psychology); Contextual image classification; Artificial neural network; Artificial intelligence; Reduction (mathematics); Network architecture; Parallel computing; Image (mathematics); Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002390499,0.0005821022,0.0002818642,0.000367636,0.0003088921,0.0004634831,0.001397655,0.0003703862,0.004369946],"category_scores_gemma":[0.000412938,0.0002699528,0.0002929195,0.000379999,0.0002055295,0.0009803053,0.0006177382,0.0007572745,0.00093138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006099903,"about_ca_system_score_gemma":0.0009787775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001929917,"about_ca_topic_score_gemma":0.004139777,"domain_scores_codex":[0.9998481,0.00001521224,0.00001170972,0.0000294564,0.0000680978,0.00002747312],"domain_scores_gemma":[0.9998236,0.00003139891,0.00001757326,0.00003073258,0.00007437757,0.00002233283],"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":[0.001064354,0.000337281,0.003027478,0.0004587459,0.0001234734,0.0005792138,0.000159706,0.07479723,0.2513852,0.03172888,0.03722589,0.5991126],"study_design_scores_gemma":[0.00009159828,0.0004819942,0.0009492264,0.00004524474,0.00006668322,0.0002873413,0.00002557118,0.8467726,0.1094011,0.006381192,0.03545988,0.00003760821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07512118,0.001348462,0.9035361,0.0004999881,0.0006160742,0.0001245737,0.000319691,0.007851831,0.01058211],"genre_scores_gemma":[0.5529127,0.0007129442,0.4271711,0.0004975217,0.0001576502,0.0001752883,0.0008546361,0.0002007131,0.01731751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004369946,"threshold_uncertainty_score":0.01461893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02644482226121408,"score_gpt":0.2436095777546586,"score_spread":0.2171647554934446,"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."}}