دورية أكاديمية

Variable-Density Self-Organizing Map for Incremental Learning

التفاصيل البيبلوغرافية
العنوان: Variable-Density Self-Organizing Map for Incremental Learning
المؤلفون: Shimada, Atsushi, Taniguchi, Rin-Ichiro
المصدر: International Workshop on Self-Organizing Maps : Proceedings (2007); The 6th International Workshop on Self-Organizing Maps (WSOM 2007) ; International Workshop on Self-Organizing Maps : Proceedings; The 6th International Workshop on Self-Organizing Maps (WSOM 2007)
بيانات النشر: Technische Fakultät, Arbeitsgruppen der Informatik
سنة النشر: 2007
المجموعة: Bielefeld University: BieColl - Bielefeld eCollections
مصطلحات موضوعية: Self-Organizing Map, Incremental Learning, DDC: 004 (Data processing, computer science, computer systems)
الوصف: We propose a new incremental learning method of Self-Organizing Map. Basically, there are three problems in the incremental learning of Self-Organizing Map: 1. depletion of neurons, 2. oblivion of training data previously given, 3. destruction of topological relationship among training samples. Weight-fixed neurons and weight-quasi-fixed neurons are very effective for the second problem. However the other problems still remain. Therefore, we improve the incremental learning method with weight-fixed neurons and weight-quasi-fixed neurons. We solve the problems by introducing a mechanism to increase the number of neurons effectively in the incremental learning process.
نوع الوثيقة: article in journal/newspaper
وصف الملف: application/pdf
اللغة: German
العلاقة: https://biecoll.ub.uni-bielefeld.de/index.php/wsom/article/view/308/401Test; https://biecoll.ub.uni-bielefeld.de/index.php/wsom/article/view/308Test
DOI: 10.2390/biecoll-wsom2007-123
الإتاحة: https://doi.org/10.2390/biecoll-wsom2007-123Test
https://biecoll.ub.uni-bielefeld.de/index.php/wsom/article/view/308Test
رقم الانضمام: edsbas.E23384B1
قاعدة البيانات: BASE