{"id":"W2975674317","doi":"10.48550/arxiv.1909.11722","title":"A Theoretical Analysis of the Number of Shots in Few-Shot Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Samsung","keywords":"Shot (pellet); Computer science; Hyperparameter; Task (project management); Set (abstract data type); Meta learning (computer science); Artificial intelligence; Machine learning; One shot; Simple (philosophy); Test (biology); Pattern recognition (psychology); Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01365933,0.002416558,0.003501327,0.003188908,0.002275376,0.004330007,0.007323336,0.005104328,0.005314282],"category_scores_gemma":[0.06333573,0.001993505,0.001968642,0.002740573,0.006642079,0.01386318,0.005090874,0.007391593,0.001196726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004473516,"about_ca_system_score_gemma":0.002065064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003710118,"about_ca_topic_score_gemma":0.00260157,"domain_scores_codex":[0.9929891,0.002013556,0.0004490114,0.002382122,0.001671036,0.0004951707],"domain_scores_gemma":[0.9429802,0.04723187,0.00204304,0.004159925,0.00255973,0.001025203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004345097,0.0003791613,0.005528514,0.001353105,0.0003716699,0.00039235,0.0008178165,0.5175779,0.004238487,0.3058211,0.005955422,0.15713],"study_design_scores_gemma":[0.0000172261,0.0001069217,0.0006839796,0.0001217817,0.00004813391,0.0001612829,0.00005690001,0.8074301,0.001536622,0.1881615,0.001633955,0.00004166024],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01249598,0.001986271,0.9813137,0.001058861,0.0001068809,0.0001036605,0.000181067,0.0004117666,0.002341797],"genre_scores_gemma":[0.549057,0.005222942,0.4310468,0.001685541,0.001231206,0.001628574,0.001347552,0.000846674,0.00793363],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01365933,"threshold_uncertainty_score":0.07223827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05509535242507704,"score_gpt":0.2129186334918856,"score_spread":0.1578232810668085,"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."}}