{"id":"W4387560181","doi":"10.48550/arxiv.2310.05566","title":"Aggregated f-average Neural Network applied to Few-Shot Class Incremental Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Task (project management); Artificial intelligence; Stack (abstract data type); Machine learning; Artificial neural network; Class (philosophy); Simple (philosophy); 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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005619865,0.000491525,0.0004910498,0.000414348,0.0004903497,0.0003724556,0.002118561,0.0002685783,0.00008355492],"category_scores_gemma":[0.0000595839,0.0006202541,0.0002342894,0.001679099,0.00006683411,0.0002980907,0.003888658,0.001485405,0.001259507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005761178,"about_ca_system_score_gemma":0.0002497463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005918297,"about_ca_topic_score_gemma":0.0002783844,"domain_scores_codex":[0.9966072,0.0003182098,0.0003606141,0.001623311,0.0002526696,0.0008380148],"domain_scores_gemma":[0.997874,0.0002156973,0.0003860339,0.0009817602,0.0001148545,0.0004276159],"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":[0.00005533732,0.00002294851,0.003075722,0.00002587088,0.00008148104,0.0003521553,0.0004952681,0.9614836,0.0001133228,0.03180445,0.0006560701,0.001833805],"study_design_scores_gemma":[0.0006804707,0.00006981817,0.004772448,0.0001001834,0.00003517021,0.000004707755,0.0003457747,0.9857467,0.00004444064,0.003586754,0.0038472,0.0007663697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3255344,0.00002610576,0.6602909,0.0003311704,0.0016796,0.00072013,0.000006096031,0.001650245,0.009761359],"genre_scores_gemma":[0.9922652,0.00004900005,0.002406852,0.0005509084,0.0001960027,0.000004508269,0.00006708795,0.00006001742,0.004400399],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6667308,"threshold_uncertainty_score":0.9996249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1051674714886787,"score_gpt":0.2064187227173172,"score_spread":0.1012512512286385,"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."}}