{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001890025,0.001450973,0.001259896,0.001210801,0.001041293,0.001321827,0.003674523,0.002704988,0.003928391],"category_scores_gemma":[0.007874032,0.000631715,0.0007925184,0.001165964,0.001604551,0.00455078,0.003161752,0.003009862,0.001498432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001549515,"about_ca_system_score_gemma":0.0007881562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002911107,"about_ca_topic_score_gemma":0.005202656,"domain_scores_codex":[0.9986084,0.0004337202,0.00004796714,0.0005975803,0.0002129612,0.00009931434],"domain_scores_gemma":[0.9974135,0.001176548,0.0001833343,0.0007502075,0.0003224092,0.0001539676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004906004,0.0004622961,0.003525148,0.0005216396,0.0002317541,0.0002606107,0.0004601768,0.3614242,0.01169806,0.09005247,0.02021494,0.5106581],"study_design_scores_gemma":[0.00001380107,0.00005492192,0.0002237382,0.00001582848,0.00001342895,0.00007413854,0.00003023546,0.9105469,0.001821813,0.08472613,0.002466615,0.00001242883],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0276541,0.0009526045,0.9647123,0.0006027306,0.000104019,0.0001391564,0.0004706075,0.001743262,0.003621129],"genre_scores_gemma":[0.6257499,0.0008154676,0.3601908,0.001128764,0.000261129,0.000553404,0.003268553,0.000401299,0.007630663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003928391,"threshold_uncertainty_score":0.01314181,"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."}}