{"id":"W4401881962","doi":"10.2139/ssrn.4937425","title":"Improving Incremental Learning: A Closer Look at the Softmax Function","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Softmax function; Function (biology); Computer science; Incremental learning; Psychology; Artificial intelligence; Deep learning; Biology; Evolutionary biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003814934,0.00102849,0.001470675,0.0009727816,0.0004972047,0.002637878,0.00237797,0.001646501,0.006115749],"category_scores_gemma":[0.02193682,0.0004321054,0.0007319883,0.001283266,0.0009313622,0.005712753,0.001760436,0.003908566,0.001574942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007403289,"about_ca_system_score_gemma":0.001481397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002894748,"about_ca_topic_score_gemma":0.002977007,"domain_scores_codex":[0.9979823,0.0007850609,0.00008935569,0.0002928274,0.0007298142,0.0001206012],"domain_scores_gemma":[0.9942807,0.003802751,0.0001527119,0.0008691275,0.0007798026,0.0001149667],"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":[0.0004208098,0.0003468519,0.001855693,0.0004143468,0.00016332,0.0001118759,0.000150665,0.09909115,0.008636986,0.07741657,0.01006963,0.801322],"study_design_scores_gemma":[0.0000372845,0.0002943185,0.001180656,0.0001083743,0.00009185295,0.0001465057,0.00004617763,0.902523,0.009279478,0.07518908,0.01106449,0.00003872821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01972893,0.00403116,0.9613578,0.00286048,0.0004356614,0.00005832208,0.0000939232,0.00150042,0.009933293],"genre_scores_gemma":[0.4880861,0.005098208,0.4848637,0.001657236,0.001273551,0.0001348352,0.000336253,0.0009503153,0.01759982],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006115749,"threshold_uncertainty_score":0.02045918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006859822693199488,"score_gpt":0.2401495790790548,"score_spread":0.2332897563858553,"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."}}