{"id":"W2952300048","doi":"10.48550/arxiv.1603.04733","title":"Structured and Efficient Variational Deep Learning with Matrix Gaussian\\n Posteriors","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Gaussian; Matrix (chemical analysis); Applied mathematics; Computer science; Artificial intelligence; Gaussian process; Statistical physics; Mathematics; Mathematical optimization; Machine learning; Physics; Materials science; Quantum mechanics","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":[0.001665095,0.0008741807,0.001013595,0.0005832282,0.0004388029,0.00137041,0.00265056,0.001464239,0.004374087],"category_scores_gemma":[0.005644515,0.0009523909,0.0008134576,0.0008270529,0.001077197,0.002411954,0.002771593,0.002818475,0.001054039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001676915,"about_ca_system_score_gemma":0.002176342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01177931,"about_ca_topic_score_gemma":0.02238591,"domain_scores_codex":[0.999333,0.0002433146,0.00002686074,0.0001238092,0.0002030294,0.00007003211],"domain_scores_gemma":[0.9989049,0.0005850742,0.0000803393,0.0001867417,0.0001612045,0.00008161504],"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":[0.00008598954,0.00005901588,0.0007820054,0.00007748323,0.00005765846,0.00007157204,0.00009381249,0.7091585,0.00181415,0.2100717,0.00487377,0.07285433],"study_design_scores_gemma":[0.000005058806,0.000004028219,0.00002536807,0.000004361013,0.000002212728,0.000006572649,0.000003164247,0.9706816,0.0001976481,0.028546,0.0005212493,0.000002782368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005218658,0.0001666458,0.9924949,0.000339406,0.00002496349,0.00002105242,0.0001558535,0.0003311965,0.001247368],"genre_scores_gemma":[0.3304256,0.0006094325,0.6572805,0.0004688979,0.0001231387,0.0001933327,0.001313705,0.0005855266,0.008999831],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01177931,"threshold_uncertainty_score":0.02342147,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01689345107360285,"score_gpt":0.1713345360625139,"score_spread":0.154441084988911,"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."}}