{"id":"W4312896061","doi":"10.1109/ijcnn55064.2022.9892722","title":"Meta-free few-shot learning via representation learning with weight averaging","year":2022,"lang":"en","type":"article","venue":"2022 International Joint Conference on Neural Networks (IJCNN)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Machine learning; Computer science; Probabilistic logic; Meta learning (computer science); Benchmark (surveying); Representation (politics); Transfer of learning; Feature learning; Range (aeronautics); Task (project management)","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008247842,0.0004153041,0.0004506241,0.0004201136,0.001063584,0.0006687339,0.001744849,0.00006348458,0.003815325],"category_scores_gemma":[0.0001394816,0.0003799558,0.0002713822,0.0007621723,0.00007984475,0.0009092194,0.001204341,0.002050044,0.00004861235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002282934,"about_ca_system_score_gemma":0.00008564203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000791588,"about_ca_topic_score_gemma":0.00002032363,"domain_scores_codex":[0.9951925,0.0008926244,0.0006165382,0.001041739,0.001692532,0.0005640427],"domain_scores_gemma":[0.9979308,0.0003426785,0.0006240384,0.0006104955,0.0003040929,0.0001879348],"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":[0.0001572633,0.00009916055,0.00140465,0.000004535649,0.0004401774,0.000168204,0.000878436,0.9374565,0.0003857127,0.03842266,0.001073943,0.01950872],"study_design_scores_gemma":[0.00123836,0.0004038866,0.001187326,0.0000259585,0.00006041323,0.0001648939,0.0003576154,0.9816679,0.00007946441,0.001193224,0.01317146,0.0004494382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007436412,0.00009939489,0.9461315,0.01145454,0.002170605,0.001539333,0.000005558992,0.0009095611,0.03025308],"genre_scores_gemma":[0.9853895,0.00003085156,0.004101557,0.001662487,0.0003011638,0.001246785,0.0001132111,0.00005210849,0.00710236],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9779531,"threshold_uncertainty_score":0.9998652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07457992658008096,"score_gpt":0.2676615434301521,"score_spread":0.1930816168500712,"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."}}