{"id":"W2963694111","doi":"10.1109/ismvl.2018.00039","title":"Efficient Hardware Realization of Convolutional Neural Networks Using Intra-Kernel Regular Pruning","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Convolutional neural network; Pruning; Realization (probability); Kernel (algebra); Artificial intelligence; Computer hardware; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001923102,0.0004485678,0.0003130739,0.0003102574,0.0002159819,0.0004790837,0.0009580649,0.0003178289,0.001448713],"category_scores_gemma":[0.0007135648,0.0001920436,0.000261597,0.0002998967,0.0002188564,0.0006518013,0.0004020153,0.0005012015,0.0005391638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003597029,"about_ca_system_score_gemma":0.0005180064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001393823,"about_ca_topic_score_gemma":0.003099258,"domain_scores_codex":[0.9998241,0.00001991305,0.00001510868,0.00002806241,0.0000754729,0.00003738706],"domain_scores_gemma":[0.9997084,0.00006431098,0.00003515355,0.0001028986,0.00007407198,0.00001514595],"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":[0.0004332647,0.0001893111,0.002232738,0.0003456703,0.0001139094,0.0007448276,0.0001855026,0.1841094,0.3011575,0.03028326,0.006769254,0.4734354],"study_design_scores_gemma":[0.00004143453,0.0002092498,0.001098219,0.00001911589,0.00003351336,0.0003140457,0.00003511165,0.874624,0.1092979,0.006541568,0.007765797,0.00001993547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2143579,0.0005783709,0.7699062,0.0001691376,0.00009930645,0.00005872702,0.000159684,0.004302462,0.01036826],"genre_scores_gemma":[0.7246199,0.0001893827,0.2718872,0.0000722817,0.00001729673,0.00005907838,0.0004521302,0.0001459671,0.002556827],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001448713,"threshold_uncertainty_score":0.004846454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02385863294850201,"score_gpt":0.2717354679041458,"score_spread":0.2478768349556437,"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."}}