{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001353823,0.0001142323,0.0001283389,0.00006721272,0.0002141684,0.00003316347,0.00045827,0.00005402451,0.000018823],"category_scores_gemma":[0.00002591368,0.0001094862,0.00004103078,0.0007426887,0.0001746874,0.0001570561,0.0002221299,0.00008293156,0.000004629059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005616101,"about_ca_system_score_gemma":0.00003472909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000155278,"about_ca_topic_score_gemma":0.000005210675,"domain_scores_codex":[0.9988304,0.00004878932,0.0002912839,0.0003424397,0.0002324696,0.0002546419],"domain_scores_gemma":[0.9989194,0.00006339788,0.0001758843,0.0004780554,0.0002914853,0.00007179721],"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":[0.000004180692,0.00002301933,0.0002617061,0.000003096898,0.000005023363,6.238024e-7,0.00007124333,0.7789872,0.002009887,0.2157162,0.0002310987,0.002686767],"study_design_scores_gemma":[0.0001318412,0.00003370479,0.0009179635,0.00001688452,0.000005014785,0.000016374,0.000009592798,0.9952096,0.00144508,0.001853576,0.0002462791,0.0001140448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03606578,0.00006043668,0.9627146,0.0001451662,0.0002262864,0.0001937906,0.000001373792,0.0001527947,0.0004397682],"genre_scores_gemma":[0.9010898,0.000002536946,0.09843111,0.0001772171,0.0002047305,0.000006619576,0.00000719641,0.000009878247,0.00007084898],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8650241,"threshold_uncertainty_score":0.4464715,"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."}}