{"id":"W2950537964","doi":"","title":"Prototypical Networks for Few-shot Learning","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Classifier (UML); Artificial intelligence; Machine learning; Metric (unit); Class (philosophy); Shot (pellet); One shot; Simple (philosophy); Inductive bias; Set (abstract data type); Metric space; Space (punctuation); Training set; Mathematics; Multi-task learning; Task (project management); 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"],"consensus_categories":[],"category_scores_codex":[0.0005362574,0.0003368067,0.0003832172,0.0001791877,0.0007619295,0.0005230897,0.002402928,0.0004204933,0.00003348112],"category_scores_gemma":[0.0002063071,0.0003950375,0.0003222827,0.0001826441,0.0001331669,0.0004274977,0.001584883,0.001184053,0.00006637517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001340286,"about_ca_system_score_gemma":0.0002131498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002717676,"about_ca_topic_score_gemma":0.00001290435,"domain_scores_codex":[0.9977551,0.0001853294,0.0002200319,0.001209698,0.0001081862,0.0005216405],"domain_scores_gemma":[0.9976633,0.0002132817,0.0004672399,0.001209104,0.0002129581,0.0002341164],"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":[0.0000820923,0.00005179101,0.001706616,0.00006735195,0.00007436057,0.00009293369,0.0002369014,0.7690635,0.00000959937,0.2221975,0.0003700644,0.006047292],"study_design_scores_gemma":[0.000673861,0.00009189768,0.0009297181,0.00009550435,0.00003494932,0.000003629254,0.00004507015,0.9610733,0.00001365356,0.01521358,0.02135976,0.0004650835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006332527,0.00005667715,0.9843696,0.000181099,0.0008029266,0.0009821518,0.000002500711,0.0004069147,0.006865598],"genre_scores_gemma":[0.9833648,0.00007268143,0.007482914,0.0001075357,0.000229778,0.00001405967,0.00002790879,0.00003070296,0.008669682],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9770322,"threshold_uncertainty_score":0.9998502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1377868834320755,"score_gpt":0.2285810279216025,"score_spread":0.09079414448952708,"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."}}