{"id":"W4403827631","doi":"10.1016/j.neucom.2024.128755","title":"Interpretable few-shot learning with online attribute selection","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Compute Canada","keywords":"Selection (genetic algorithm); Computer science; Artificial intelligence; Shot (pellet); Machine learning; Feature selection; Pattern recognition (psychology); One shot","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":[0.0025988,0.001284266,0.00268891,0.001390515,0.0008260699,0.001612617,0.00315529,0.002557267,0.002190147],"category_scores_gemma":[0.009154156,0.0008050715,0.001333996,0.001346614,0.001221292,0.003127694,0.002611969,0.003449797,0.0007199816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007768983,"about_ca_system_score_gemma":0.0009445498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002687514,"about_ca_topic_score_gemma":0.0032642,"domain_scores_codex":[0.9983168,0.000683221,0.00009239049,0.0005249157,0.0002579309,0.0001248295],"domain_scores_gemma":[0.9955461,0.003128877,0.0001819019,0.0005892067,0.0003921919,0.0001615896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006431072,0.0008178506,0.002933627,0.0004684761,0.0005386961,0.0003999334,0.0003510039,0.4334243,0.01080431,0.02593223,0.009919412,0.513767],"study_design_scores_gemma":[0.000009940713,0.00003056494,0.0002075528,0.00001049706,0.00001691902,0.00003930054,0.00001412868,0.9788826,0.0009466216,0.01955735,0.0002725258,0.00001206481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01422408,0.0007428398,0.9835086,0.0002703108,0.00007699824,0.00004360215,0.0001013796,0.0005793607,0.0004527138],"genre_scores_gemma":[0.685902,0.0007511053,0.3058798,0.0006603329,0.000388438,0.0002465093,0.001324249,0.0002341274,0.004613415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00315529,"threshold_uncertainty_score":0.013744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02122622023472021,"score_gpt":0.2641693199121464,"score_spread":0.2429430996774262,"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."}}