{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001536211,0.0001082318,0.0001264649,0.00009769351,0.0001854794,0.00004509756,0.0003596923,0.00002691299,0.00001056757],"category_scores_gemma":[0.000005177102,0.0001001526,0.0000472579,0.001169838,0.00002917147,0.0002537963,0.000224219,0.00006319462,0.00000640236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000264182,"about_ca_system_score_gemma":0.0000226013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001088187,"about_ca_topic_score_gemma":0.000004522873,"domain_scores_codex":[0.9989303,0.00002592854,0.0002591289,0.000325964,0.0001436516,0.0003150639],"domain_scores_gemma":[0.9991825,0.0002220474,0.0001271473,0.0002976707,0.000118105,0.00005256624],"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":[0.000002839511,0.00001823909,0.00009049786,0.00000671521,0.00001121543,0.000001133341,0.0003318313,0.6162506,0.00152534,0.0219032,0.002584879,0.3572735],"study_design_scores_gemma":[0.0003427417,0.00009552782,0.0007951073,0.000004951969,0.000004077969,0.000001686344,0.0001884084,0.9947712,0.002534642,0.0007431988,0.0004140992,0.0001043247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0143914,0.00002905676,0.9837766,0.0005512162,0.0002692361,0.0006630535,0.00001061063,0.0002584274,0.00005041128],"genre_scores_gemma":[0.7680663,0.00001292926,0.2305256,0.0002042797,0.0001425142,0.000400191,0.00007808107,0.00001889068,0.0005511924],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7536749,"threshold_uncertainty_score":0.4084106,"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."}}