{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000161889,0.0005472373,0.0005120802,0.0002427738,0.0005418722,0.0002177693,0.001605653,0.0003284812,0.000008664842],"category_scores_gemma":[0.000023216,0.0004691365,0.0001537542,0.0009715129,0.0002306608,0.001024316,0.001615191,0.0009124979,0.000004786109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001267325,"about_ca_system_score_gemma":0.00007587397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001121016,"about_ca_topic_score_gemma":0.0000329858,"domain_scores_codex":[0.9969077,0.0002082634,0.0003227691,0.001729247,0.0001478765,0.0006842163],"domain_scores_gemma":[0.9967804,0.0006998319,0.0004957318,0.0015133,0.0001832736,0.0003274492],"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":[0.00009301148,0.00003968195,0.0007528321,0.00001096703,0.00005158148,0.00007026015,0.0001053478,0.9401237,0.00001501389,0.04768837,0.00008305079,0.01096616],"study_design_scores_gemma":[0.0007942426,0.00007754003,0.001540608,0.0001582077,0.0000519013,0.00002474082,0.00002287494,0.9778835,0.0000128258,0.01872091,0.0001303054,0.0005823483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1629161,0.000111341,0.8349369,0.0003674465,0.000386534,0.0006319229,0.000006885244,0.0004216298,0.0002212403],"genre_scores_gemma":[0.9926036,0.0002576617,0.006275726,0.0001550205,0.0002918411,0.00001113277,0.00002316727,0.00004633784,0.000335527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8296875,"threshold_uncertainty_score":0.999776,"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."}}