{"id":"W2950894517","doi":"","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"MNIST database; Computer science; Artificial neural network; Binary number; Multiplication (music); Kernel (algebra); Computation; Algorithm; Treebank; Artificial intelligence; Code (set theory); Byte; Deep neural networks; Arithmetic; 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":[0.0007444478,0.001013318,0.0005798339,0.000528564,0.0003283172,0.0009134237,0.00238593,0.0007453408,0.005967311],"category_scores_gemma":[0.004090087,0.0007040855,0.0004055071,0.0007839316,0.0007250251,0.002115536,0.001119923,0.001673339,0.001354998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001096381,"about_ca_system_score_gemma":0.0009684035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007731071,"about_ca_topic_score_gemma":0.01332623,"domain_scores_codex":[0.9995611,0.00006922792,0.00003097981,0.0001299341,0.0001541443,0.00005456205],"domain_scores_gemma":[0.9993778,0.0002150621,0.00006775684,0.0001687693,0.0001457471,0.00002479278],"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":[0.0003193853,0.0001569308,0.001814265,0.0003419057,0.0001336462,0.0001609554,0.0001572724,0.5434553,0.02922611,0.02763719,0.01464404,0.381953],"study_design_scores_gemma":[0.00002371929,0.00005151003,0.000199443,0.00001512295,0.00001158372,0.00003228073,0.00001237291,0.9800315,0.008868021,0.00829335,0.0024512,0.000009960186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01991499,0.0003052455,0.9700144,0.0002022671,0.0001406949,0.00009682091,0.0005183968,0.006655696,0.002151472],"genre_scores_gemma":[0.3508638,0.000359671,0.6399991,0.0003066975,0.00006960738,0.0004366031,0.001471557,0.0007119769,0.005781013],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007731071,"threshold_uncertainty_score":0.01996267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0561029340910995,"score_gpt":0.2058466194603517,"score_spread":0.1497436853692523,"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."}}