{"id":"W2809263290","doi":"10.48550/arxiv.1807.00942","title":"Stochastic Layer-Wise Precision in Deep Neural Networks","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"MNIST database; Computer science; Memory footprint; Regularization (linguistics); Artificial neural network; Convolutional neural network; Deep neural networks; Generalization; Artificial intelligence; Implementation; Deep learning; Machine learning; 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":[0.003450499,0.001107487,0.00100261,0.000719558,0.0005880427,0.001468211,0.001619502,0.00157985,0.001051554],"category_scores_gemma":[0.01427002,0.0008938378,0.0006748356,0.0007624145,0.002768928,0.002776998,0.002664326,0.002796135,0.0002929712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001449849,"about_ca_system_score_gemma":0.0009158637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001820634,"about_ca_topic_score_gemma":0.001602686,"domain_scores_codex":[0.99837,0.0005205912,0.000113291,0.0003659642,0.0004752459,0.0001549278],"domain_scores_gemma":[0.9958777,0.00248149,0.0005499928,0.0007075227,0.0002796336,0.000103577],"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":[0.0001332611,0.00002225938,0.0006516694,0.00006691021,0.00004271469,0.00007609824,0.00006835937,0.9161587,0.005524013,0.05290491,0.0005567028,0.02379433],"study_design_scores_gemma":[0.0000151649,0.00005834788,0.0001924259,0.00002306767,0.00001229138,0.00003546584,0.000005766242,0.9413017,0.003752089,0.05415842,0.0004329781,0.00001225152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05917863,0.0008089924,0.9365492,0.0005033403,0.00004930243,0.00003226571,0.00007774415,0.0007438252,0.00205666],"genre_scores_gemma":[0.9125718,0.0006067601,0.0840953,0.0002235379,0.00008302691,0.00008959875,0.0001109322,0.0001762786,0.002042762],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003450499,"threshold_uncertainty_score":0.0182482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05264411588032774,"score_gpt":0.2122809903390949,"score_spread":0.1596368744587672,"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."}}