{"id":"W4400230701","doi":"10.1109/iscas58744.2024.10558100","title":"BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization","year":2024,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; University of Toronto","funders":"","keywords":"Computer science; Quantization (signal processing); Artificial intelligence; Computer vision","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":[0.001515484,0.001169087,0.000938053,0.0008248031,0.0006745424,0.001429757,0.002784,0.00133747,0.007967797],"category_scores_gemma":[0.0126451,0.0005554736,0.0005013499,0.00101794,0.001283692,0.003496914,0.002404366,0.002569044,0.002864677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001051944,"about_ca_system_score_gemma":0.001318167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002813105,"about_ca_topic_score_gemma":0.005748309,"domain_scores_codex":[0.9989341,0.0002327378,0.0001118285,0.0002915983,0.0003320672,0.00009763102],"domain_scores_gemma":[0.9973931,0.0009484626,0.0002134621,0.0008929942,0.0004617888,0.00009011004],"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":[0.001110021,0.0002856256,0.002970484,0.0003543333,0.0001047374,0.0001828319,0.0003502316,0.205352,0.04418922,0.03574003,0.02736136,0.6819992],"study_design_scores_gemma":[0.0001015381,0.0001464131,0.0003670271,0.00006686986,0.00002074084,0.0001119138,0.00005647157,0.9344026,0.02605496,0.03272588,0.005905152,0.00004036618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04790442,0.0009832729,0.9343209,0.000663688,0.0002696846,0.0001556375,0.0006401873,0.01125248,0.003809679],"genre_scores_gemma":[0.3915298,0.0004505814,0.5969458,0.0007054661,0.0001183762,0.0004684741,0.00155534,0.002349158,0.005877116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007967797,"threshold_uncertainty_score":0.02665496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01725010138011467,"score_gpt":0.2906922842177659,"score_spread":0.2734421828376513,"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."}}