Algorithms and Implementation Architectures for Hebbian Neural Networks
| dc.contributor.author | Berzal, José Andrés | |
| dc.contributor.author | Zufiria, Pedro | |
| dc.date.accessioned | 2024-02-09T08:38:57Z | |
| dc.date.available | 2024-02-09T08:38:57Z | |
| dc.date.issued | 2001 | |
| dc.identifier.issn | 978-3-540-42235-8 | |
| dc.identifier.issn | 978-3-540-45720-6 | |
| dc.identifier.uri | https://hdl.handle.net/10115/30168 | |
| dc.description | Las Redes Neuronales de Sanger y Rubner son analizadas desde el punto de vista de sistemas dinámicos por lo que se establecen criterios sobre su estabilidad. Se identifica una de sus principales aplicaciones, Análisis de Componente Principales )PCA). Además, se proponen arquitecturas para dichas Redes Neuronales que optimizan la ejecución por máquina de dichas redes. Representan primeras propuesta de algoritmos y arquitectura para Inteligencia Artificial. | es |
| dc.description.abstract | Systolic architectures for Sanger and Rubner Neural Networks (NNs) are proposed, and the local stability of their learning rules is taken into account based on the indirect Lyapunov method. In addition, these learning rules are improved for applications based on Principal Component Analysis (PCA). The local stability analysis and the systolic architectures for Sanger NN and Rubner NN are presented in a common framework. | es |
| dc.language.iso | eng | es |
| dc.publisher | Springer, Berlin, Heidelberg | es |
| dc.subject | Hebbian Neural Network | es |
| dc.subject | Systolic architectures | es |
| dc.subject | Stability | es |
| dc.subject | Artificial Intelligence Algorithms | es |
| dc.subject | Principal Component Analysis | es |
| dc.title | Algorithms and Implementation Architectures for Hebbian Neural Networks | es |
| dc.type | info:eu-repo/semantics/article | es |
| dc.identifier.doi | 10.1007/3-540-45720-8_20 | es |
| dc.rights.accessRights | info:eu-repo/semantics/embargoedAccess | es |
Files in this item
This item appears in the following Collection(s)
Los ítems de digital-BURJC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario