Combinatorial Learning and Associative Learning in Hyper-Column Model
العنوان: | Combinatorial Learning and Associative Learning in Hyper-Column Model |
---|---|
المؤلفون: | Taniguchi Rin-ichiro, Shimada Atsushi, Tsuruta Naoyuki |
المصدر: | The Brain & Neural Networks. 13:129-136 |
بيانات النشر: | Japanese Neural Network Society, 2006. |
سنة النشر: | 2006 |
مصطلحات موضوعية: | Artificial neural network, Computer science, Position (vector), business.industry, Orientation (computer vision), Two layer, Pattern recognition, Neocognitron, Artificial intelligence, Object (computer science), business, Column model, Associative learning |
الوصف: | Hyper-Column Model (HCM) is a self-organized, competitive and hierarchical multilayer neural network. It is derived from the Neocognitron by replacing each S cell and C cell with a two layer Hierarchical Self-Organizing Map (HSOM). HCM can recognize images with variant object size, position, orientation and spatial resolution. In this paper, we propose two new learning methods; “Combinatorial Learning, ” and “Associative Learning”. The former enables HCM to learn a pattern of winner neurons which are activated in each HSOM with excitatory lateral connections. HCM is expanded to a supervised learnable model by the latter learning algorithm. |
تدمد: | 1883-0455 1340-766X |
الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_________::45d0e8e2b70027312761c3b8e7d262e6Test https://doi.org/10.3902/jnns.13.129Test |
حقوق: | OPEN |
رقم الانضمام: | edsair.doi...........45d0e8e2b70027312761c3b8e7d262e6 |
قاعدة البيانات: | OpenAIRE |
تدمد: | 18830455 1340766X |
---|