{"id":"W3086607822","doi":"","title":"'Less Than One'-Shot Learning: Learning N Classes From M<N Samples","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Classifier (UML); Machine learning; Generalization; One shot; Shot (pellet); Artificial neural network; Robustness (evolution); Class (philosophy); Task (project management); Training set; Single shot; Pattern recognition (psychology); Mathematics; Engineering","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.000318064,0.0005303923,0.0006333924,0.0003097731,0.0005158059,0.000581864,0.002488049,0.000425201,0.0001507683],"category_scores_gemma":[0.0003204594,0.0006754639,0.0003051397,0.0007948707,0.0001517343,0.0005468726,0.002886325,0.00257724,0.000381154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002034535,"about_ca_system_score_gemma":0.0003338237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006970204,"about_ca_topic_score_gemma":0.00009732872,"domain_scores_codex":[0.996188,0.0006932344,0.0003527942,0.001915147,0.0002767158,0.0005740844],"domain_scores_gemma":[0.9973345,0.0005818701,0.0005802776,0.000899471,0.0001894811,0.0004143524],"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":[0.00008822283,0.0001348054,0.03710177,0.0001016725,0.0003688984,0.0004886975,0.00352437,0.7721754,0.0007686307,0.1790962,0.0002381039,0.005913233],"study_design_scores_gemma":[0.00106596,0.0002126921,0.02144363,0.0002781676,0.0001637191,0.000003708528,0.00391076,0.9067935,0.0002719405,0.03761535,0.02670364,0.001536982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2282403,0.0001057907,0.7602939,0.0004592788,0.0005298263,0.0002166494,0.000009666838,0.001051262,0.009093393],"genre_scores_gemma":[0.9888501,0.0002915382,0.007361191,0.0002232174,0.0002228928,0.000001629397,0.0001344303,0.00005236444,0.002862672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7606098,"threshold_uncertainty_score":0.9997239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2616300794238546,"score_gpt":0.2222294257833783,"score_spread":0.03940065364047632,"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."}}