{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001836541,0.0007291567,0.0006791664,0.0003755351,0.0003699793,0.0006656286,0.003577907,0.0004550029,0.00008259484],"category_scores_gemma":[0.00006969142,0.0007375475,0.0001666025,0.002183952,0.0002448511,0.001032221,0.001445374,0.001075967,0.0001572792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002899826,"about_ca_system_score_gemma":0.001527117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009233801,"about_ca_topic_score_gemma":0.0001453163,"domain_scores_codex":[0.995838,0.0001537236,0.0004410706,0.002499752,0.0003430255,0.0007244435],"domain_scores_gemma":[0.9963742,0.00008751093,0.0007139188,0.001779974,0.0005036048,0.0005408171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008944249,0.001555146,0.02146696,0.006036192,0.0009995644,0.002085683,0.003375379,0.01567647,0.000592609,0.9381683,0.002287884,0.006861315],"study_design_scores_gemma":[0.003421194,0.00139271,0.02628066,0.002595953,0.0007202869,0.00008774451,0.0008796449,0.8038514,0.002750813,0.1486765,0.004593838,0.00474931],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009583072,0.00007312286,0.9745954,0.00298675,0.000242138,0.000685767,0.00003188288,0.0007573547,0.01104448],"genre_scores_gemma":[0.9886044,0.0002334747,0.00957652,0.0003526229,0.0001380883,0.0000107197,0.00008802428,0.00005396076,0.0009421522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9790214,"threshold_uncertainty_score":0.9995075,"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."}}