{"id":"W3134055916","doi":"10.1109/tcsi.2021.3060945","title":"A Real-Time Architecture for Pruning the Effectual Computations in Deep Neural Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems I Regular Papers","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pruning; Benchmark (surveying); Computation; Computer science; Inference; Artificial neural network; Dataflow; Speedup; Filter (signal processing); Algorithm; Artificial intelligence; Theoretical computer science; Parallel computing; Computer engineering","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002254211,0.0001933936,0.0002469419,0.00008856666,0.0005530389,0.0001769873,0.0003045043,0.00009115227,0.000002393934],"category_scores_gemma":[0.00001189739,0.0001550832,0.0001060687,0.0006535883,0.00008012314,0.0001268242,0.000004622941,0.0002691301,0.000002076112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005069758,"about_ca_system_score_gemma":0.0000403275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001515001,"about_ca_topic_score_gemma":0.00007906154,"domain_scores_codex":[0.9984314,0.000248593,0.0002987722,0.0004995521,0.000182378,0.0003393197],"domain_scores_gemma":[0.9982489,0.0009760172,0.00008380395,0.000501203,0.00006929941,0.0001207166],"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":[0.000003495419,0.00003191768,0.000002963836,0.00002382081,0.00002209987,0.000007475715,0.0005216192,0.903243,0.004058897,0.002265285,0.0000188144,0.08980059],"study_design_scores_gemma":[0.0004660353,0.00006726255,0.0001377052,0.00004958473,0.00002115473,0.0001699663,0.0001294356,0.9976844,0.0002317515,0.0002321586,0.0006200823,0.0001905325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007976213,0.0002919463,0.9891917,0.0009470226,0.0003711052,0.0008716279,0.000008304254,0.000129774,0.0002122741],"genre_scores_gemma":[0.9972315,0.00004479159,0.001814061,0.0001897186,0.00007783729,0.0004050088,0.00000614687,0.00002335883,0.0002075683],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9892553,"threshold_uncertainty_score":0.6324109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0122074637905038,"score_gpt":0.2323241430116404,"score_spread":0.2201166792211366,"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."}}