{"id":"W2952193948","doi":"10.1109/icpr48806.2021.9412010","title":"Meta Learning via Learned Loss","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"International Max Planck Research School for Advanced Methods in Process and Systems Engineering; York University; European Commission; International Max Planck Research School for Environmental, Cellular and Molecular Microbiology; National Science Foundation","keywords":"Computer science; Reinforcement learning; Machine learning; Artificial intelligence; Parametric statistics; Regularization (linguistics); Pipeline (software); Code (set theory); Set (abstract data type); Meta learning (computer science); Process (computing); Source code; Function (biology); Task (project management); Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001083706,0.0005557619,0.0009645903,0.0002126276,0.0002888336,0.0009915122,0.0029361,0.0004784049,0.000946539],"category_scores_gemma":[0.0003890844,0.0005138572,0.0006680057,0.0004484592,0.0000760213,0.0005041677,0.01077796,0.003505405,0.000149336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001137571,"about_ca_system_score_gemma":0.0003236913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003866205,"about_ca_topic_score_gemma":0.00002480308,"domain_scores_codex":[0.9957689,0.0007860196,0.0005217958,0.001596657,0.0007487208,0.0005778796],"domain_scores_gemma":[0.9970586,0.0003229344,0.0004097038,0.001789414,0.0002439627,0.0001753406],"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":[0.000004799974,0.00005842444,0.0006486781,0.0001244935,0.002071648,0.0004142199,0.001335117,0.9480933,0.0001102111,0.01476713,0.0001222545,0.03224971],"study_design_scores_gemma":[0.0003149047,0.00004132873,0.0002968122,0.00006389526,0.0007045487,0.0000785941,0.0001040447,0.9823691,0.0005365692,0.008397821,0.005982996,0.001109357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001489506,0.0008169166,0.9802766,0.002241606,0.001690123,0.000193219,3.581999e-7,0.001133464,0.01215819],"genre_scores_gemma":[0.5723515,0.00009469259,0.4165232,0.0004446984,0.0003382516,0.00005402361,0.00003860946,0.00006620461,0.01008881],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.570862,"threshold_uncertainty_score":0.9999667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05842071702153865,"score_gpt":0.3002474851927516,"score_spread":0.2418267681712129,"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."}}