{"id":"W4294969213","doi":"10.1609/aaai.v35i11.17171","title":"`Less Than One'-Shot Learning: Learning N Classes From M < N Samples","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Shot (pellet); Class (philosophy); Artificial intelligence; Task (project management); Computer science; Machine learning; Training (meteorology); One shot; Artificial neural network; 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":[0.0005945309,0.0003129448,0.0004122028,0.0001406864,0.0005369951,0.0008188283,0.001852557,0.000147549,0.0002689113],"category_scores_gemma":[0.001902085,0.0002764353,0.0001731544,0.0009643205,0.0002597641,0.0005786262,0.0006618166,0.0009276477,0.0001706805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005816515,"about_ca_system_score_gemma":0.0002464817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001017021,"about_ca_topic_score_gemma":0.00005008971,"domain_scores_codex":[0.9970478,0.0001120072,0.0006661019,0.0008310939,0.000842286,0.0005007521],"domain_scores_gemma":[0.9974599,0.0004462154,0.0005819171,0.000349122,0.001001877,0.0001609488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004621208,0.0001769268,0.002858578,0.00002988402,0.00004530172,0.0000029092,0.003897389,0.00108817,0.1632196,0.7200461,0.00006396619,0.108525],"study_design_scores_gemma":[0.00009655739,0.0003066227,0.003978695,0.0005704224,0.00003867858,0.000009654584,0.01277261,0.10399,0.7442041,0.1285079,0.004834296,0.0006905055],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7146682,0.0002466574,0.2099952,0.00814593,0.00113204,0.000459251,0.000007812137,0.000615871,0.06472897],"genre_scores_gemma":[0.9884552,0.0001368686,0.009473722,0.000253537,0.000125609,0.00001789025,0.000004699556,0.00002495136,0.001507527],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5915382,"threshold_uncertainty_score":0.9999688,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2065969663041616,"score_gpt":0.315659843378008,"score_spread":0.1090628770738465,"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."}}