{"id":"W4415028296","doi":"10.1007/978-981-95-1999-6_12","title":"NormSoftmax Attention: Improving Transformer Model Performance","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in electrical engineering","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Adaptability; Transformer; Flexibility (engineering); Focus (optics); SIGNAL (programming language); Personalization","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":[0.002190017,0.002597655,0.001374522,0.0007034718,0.0004970843,0.001770148,0.002676463,0.001776291,0.0114428],"category_scores_gemma":[0.008310802,0.0006815692,0.0006415943,0.0007271597,0.0005526156,0.003656426,0.002947771,0.002760099,0.003358501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009601117,"about_ca_system_score_gemma":0.001169934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006888836,"about_ca_topic_score_gemma":0.01166926,"domain_scores_codex":[0.9986849,0.0004497196,0.0000709962,0.0002538511,0.0004027963,0.0001378283],"domain_scores_gemma":[0.9974884,0.001230035,0.0001044038,0.000469797,0.0006163227,0.00009107039],"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":[0.0007334265,0.0002503293,0.0006994268,0.0001668106,0.0001061653,0.00007394302,0.00006760693,0.1071682,0.01213481,0.009988689,0.01924244,0.8493683],"study_design_scores_gemma":[0.00002101408,0.00005817071,0.0001358926,0.000008725004,0.00002429749,0.00002548406,0.00001239374,0.9825053,0.007859186,0.007948534,0.001392889,0.000008033052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02404975,0.001648505,0.9610763,0.0005681663,0.0004835957,0.00005457465,0.0003284362,0.006461723,0.00532899],"genre_scores_gemma":[0.5751277,0.001334398,0.3903365,0.0008514758,0.0005882466,0.0002025702,0.002243164,0.002816777,0.02649919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0114428,"threshold_uncertainty_score":0.03828001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005979224417218525,"score_gpt":0.1904811787473016,"score_spread":0.1845019543300831,"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."}}