{"id":"W3045212685","doi":"10.48550/arxiv.2007.10417","title":"Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Softmax function; Overfitting; Artificial intelligence; Bayesian probability; Classifier (UML); Computer science; Gaussian process; Machine learning; Gaussian; One shot; Posterior probability; Single shot; Shot (pellet); Pattern recognition (psychology); Deep learning; Physics","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":[0.005497626,0.001448506,0.002335251,0.001241653,0.001382142,0.002576625,0.004110515,0.003317023,0.002989862],"category_scores_gemma":[0.01630337,0.000727394,0.001523271,0.001284556,0.001910208,0.003913017,0.003937752,0.005533503,0.001519502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001909718,"about_ca_system_score_gemma":0.00203136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008494395,"about_ca_topic_score_gemma":0.009844086,"domain_scores_codex":[0.9975268,0.0007875579,0.0001017892,0.0007633175,0.0005671664,0.000253236],"domain_scores_gemma":[0.9924011,0.004660848,0.0003712751,0.001404598,0.0008468099,0.0003154054],"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":[0.0009324022,0.0005294131,0.00343533,0.0002702473,0.0001522401,0.0002516815,0.0005203744,0.4726779,0.007077497,0.04528571,0.01123482,0.4576325],"study_design_scores_gemma":[0.00001118766,0.00002190829,0.0001981057,0.00001089378,0.000007454502,0.00002365909,0.00002211516,0.9755372,0.00130469,0.02238,0.0004706545,0.00001207905],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02666991,0.0003895385,0.9688516,0.0004836087,0.00008769805,0.0001131618,0.0002178779,0.001737395,0.001449244],"genre_scores_gemma":[0.5998677,0.0003816208,0.3901627,0.0009022121,0.0002528186,0.0003304215,0.001979943,0.0004424296,0.005680242],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008494395,"threshold_uncertainty_score":0.02907455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1120809691058499,"score_gpt":0.2043536822460003,"score_spread":0.09227271314015043,"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."}}