{"id":"W4385624928","doi":"10.1109/newcas57931.2023.10198137","title":"Iterative pruning algorithm for efficient look-up table implementation of binary neural networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Field-programmable gate array; Pruning; Lookup table; Throughput; Artificial neural network; Algorithm; Power consumption; Table (database); Binary number; Layer (electronics); Parallel computing; Power (physics); Computer hardware; Artificial intelligence; Arithmetic; Mathematics; Data mining","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":[0.0003188651,0.0006002803,0.0003668451,0.0008055983,0.0003981523,0.0007362823,0.001318092,0.0003971612,0.007121527],"category_scores_gemma":[0.001357998,0.0003361643,0.0003671215,0.0007708538,0.0001836024,0.0008649016,0.000432037,0.0005956909,0.001630342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004813067,"about_ca_system_score_gemma":0.001070262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003155234,"about_ca_topic_score_gemma":0.007519768,"domain_scores_codex":[0.9996178,0.00006412126,0.00004584306,0.0000465935,0.0001717995,0.00005376009],"domain_scores_gemma":[0.9995579,0.0001535668,0.00004969299,0.00006978523,0.0001527113,0.00001627182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004360564,0.0001456357,0.00101509,0.0003306862,0.00008919153,0.0003357118,0.0001782864,0.04222744,0.08494863,0.01534197,0.01558356,0.8393678],"study_design_scores_gemma":[0.0001648533,0.0005072877,0.001121566,0.00008654041,0.00008927422,0.0005861615,0.00007711449,0.8552845,0.1066784,0.008751173,0.02660268,0.00005050968],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04234952,0.001294974,0.9433892,0.0001953311,0.0001355615,0.0001226971,0.0002140704,0.005795353,0.006503288],"genre_scores_gemma":[0.2259609,0.0003729357,0.766946,0.0001815382,0.00003783673,0.0002205176,0.0006362969,0.0002678569,0.00537621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007121527,"threshold_uncertainty_score":0.02382392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02417174386502194,"score_gpt":0.3218719143179041,"score_spread":0.2977001704528822,"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."}}