{"id":"W4413407284","doi":"10.1016/j.neunet.2025.108017","title":"Rethinking softmax in incremental learning","year":2025,"lang":"en","type":"article","venue":"Neural Networks","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Softmax function; Artificial intelligence; Computer science; Incremental learning; Machine learning; Pattern recognition (psychology); Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004062335,0.0001031357,0.0001204943,0.0001384175,0.0001762095,0.0001854609,0.0004318235,0.0000731449,0.0000184799],"category_scores_gemma":[0.00007148016,0.0001064679,0.00004211221,0.0006691968,0.00002499525,0.0003088224,0.0002487705,0.0006378412,0.0000101388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000531694,"about_ca_system_score_gemma":0.00002109569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002812623,"about_ca_topic_score_gemma":0.00003113023,"domain_scores_codex":[0.9988858,0.0001634651,0.0002134706,0.0002870017,0.000155389,0.0002949506],"domain_scores_gemma":[0.9995369,0.0001645248,0.00005974794,0.0001765382,0.00002135437,0.00004088842],"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":[0.00001909732,0.00003086765,0.03689712,0.00001010861,0.00001098748,0.00005803915,0.001616077,0.5723697,0.0002521604,0.04417938,0.0007671261,0.3437893],"study_design_scores_gemma":[0.000315728,0.00002218165,0.0102729,0.00003962326,0.000001367705,0.00000335404,0.0000520703,0.9845242,0.00002359146,0.001605724,0.003038845,0.0001004137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1021382,0.0004780428,0.870334,0.001670849,0.001166722,0.0001749953,5.707858e-8,0.0004358848,0.02360129],"genre_scores_gemma":[0.9924524,0.00001573737,0.004789982,0.001813694,0.00005603032,0.000006595759,0.000002473897,0.000005827275,0.0008572551],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8903142,"threshold_uncertainty_score":0.4341635,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647509025716623,"score_gpt":0.2534884894029195,"score_spread":0.2370133991457532,"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."}}