{"id":"W2963939004","doi":"","title":"Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Variance reduction; Computer science; Multiplicative function; Control variates; Gaussian; Stochastic gradient descent; Regularization (linguistics); Importance sampling; Convolutional neural network; Artificial neural network; Reduction (mathematics); Algorithm; Variance (accounting); Bayesian probability; Artificial intelligence; Machine learning; Monte Carlo method; Mathematics; Markov chain Monte Carlo; Statistics","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":[0.001989912,0.001885534,0.001213786,0.0005170462,0.0005741786,0.0007891656,0.003479922,0.001611439,0.005908203],"category_scores_gemma":[0.01014458,0.0009947063,0.0007965432,0.0005053152,0.001013516,0.002083655,0.001950747,0.002534875,0.001963513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028042,"about_ca_system_score_gemma":0.001833681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004645403,"about_ca_topic_score_gemma":0.007833313,"domain_scores_codex":[0.9991689,0.0002392136,0.00006293018,0.0001814818,0.0002492419,0.00009824255],"domain_scores_gemma":[0.9972805,0.001224989,0.0001991093,0.0006386335,0.000480278,0.0001764446],"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":[0.0009213245,0.0004261776,0.001804754,0.0002766162,0.0001559736,0.0002305278,0.0001802348,0.6105864,0.02883212,0.01371464,0.01835585,0.3245154],"study_design_scores_gemma":[0.00005544414,0.00005239972,0.0000987207,0.000007912156,0.000007855128,0.0000227518,0.000008092915,0.9900196,0.005155236,0.00366383,0.0008981596,0.00001003605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02659621,0.0002725795,0.9599839,0.000208777,0.0002237054,0.0002655559,0.0002339048,0.01029373,0.00192172],"genre_scores_gemma":[0.3423533,0.0001938164,0.6470788,0.0005216785,0.0001521377,0.0009005208,0.001230258,0.002368483,0.005201016],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005908203,"threshold_uncertainty_score":0.01976484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04482411746879406,"score_gpt":0.1925983170088435,"score_spread":0.1477741995400494,"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."}}