{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005271024,0.000439032,0.0004587508,0.000465077,0.0001842238,0.0001677613,0.003131401,0.0004831376,0.0000491459],"category_scores_gemma":[0.0002058879,0.0005158482,0.0001920384,0.0009625623,0.0001296141,0.0005689457,0.005392493,0.001571598,0.00006871373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003442658,"about_ca_system_score_gemma":0.0000984877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001608296,"about_ca_topic_score_gemma":0.0001610217,"domain_scores_codex":[0.9969688,0.0004016193,0.0003160688,0.001554649,0.0001529305,0.0006059501],"domain_scores_gemma":[0.9973887,0.0003547412,0.0003508532,0.001563863,0.000147045,0.0001947897],"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":[0.00004749198,0.00004751567,0.001852498,0.00001779607,0.0000203771,0.0002814696,0.0002341509,0.986023,0.000001249747,0.008934477,0.00003938517,0.002500597],"study_design_scores_gemma":[0.0005540169,0.00005888874,0.001698966,0.0001110107,0.00002880076,0.000006034078,0.00002659759,0.9802226,0.000001786177,0.01678815,0.00001904966,0.0004840666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1228085,0.00007297725,0.8742397,0.0000648663,0.001744269,0.000330469,0.000001408539,0.0002648981,0.0004728302],"genre_scores_gemma":[0.994975,0.00001921196,0.004389664,0.00006767268,0.0003012009,0.000001398768,0.00001056602,0.00003255468,0.0002027197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8721665,"threshold_uncertainty_score":0.9997293,"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."}}