{"id":"W2114508814","doi":"","title":"Low precision arithmetic for deep learning","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"MNIST database; Computer science; Benchmark (surveying); Computation; Artificial neural network; Point (geometry); Set (abstract data type); Floating point; Artificial intelligence; Training set; Deep learning; Algorithm; Machine learning; Arithmetic; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001295019,0.00007428374,0.00008043111,0.0000494933,0.0002126747,0.00005219142,0.0005180779,0.00003775539,0.00000597128],"category_scores_gemma":[0.00002698188,0.00007696942,0.00006209295,0.0003599431,0.00002473569,0.0002210574,0.0001275072,0.00008741282,0.00005479833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001877216,"about_ca_system_score_gemma":0.000007385881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000357285,"about_ca_topic_score_gemma":0.000005687332,"domain_scores_codex":[0.9993356,0.00003802686,0.00006614615,0.0003515824,0.0000314816,0.0001771477],"domain_scores_gemma":[0.9992933,0.0002099593,0.00005206306,0.0003151765,0.00005393842,0.00007556144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008366003,0.00005166665,0.0005404216,0.000008570044,0.000007267307,0.000003565137,0.00004241436,0.226058,0.0002946757,0.6966972,0.0002675976,0.07602023],"study_design_scores_gemma":[0.0002329899,0.00006831428,0.0005088461,0.000007765393,0.000006226702,0.000001235189,0.000006526647,0.9570364,0.000304102,0.03051969,0.01120512,0.0001027993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06846805,0.000007288185,0.9301043,0.0001094263,0.00007435238,0.000122356,2.526052e-7,0.0001128748,0.001001093],"genre_scores_gemma":[0.9926197,0.00001578015,0.005757469,0.00009027498,0.00005230562,0.000001170369,0.000001630833,0.000005444751,0.001456223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9243469,"threshold_uncertainty_score":0.3138722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03463392661948356,"score_gpt":0.1742007141424249,"score_spread":0.1395667875229414,"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."}}