HANNA: a tool for hardware prototyping and benchmarking of ANNs. Póster
Ver/
Identificadores
URI: http://hdl.handle.net/10317/908ISSN: 0302-9743 (Print) 1611-3349 (Online)
ISBN: 978-3-540-73054-5
Compartir
Estadísticas
Ver Estadísticas de usoMetadatos
Mostrar el registro completo del ítemAutor
Garrigós Guerrero, Francisco Javier; Martínez Álvarez, José Javier; Ferrández Vicente, José Manuel; Toledo Moreo, Francisco JavierGrupo de investigación
Grupo Dispositivos y Diseño Microelectrónico; Grupo Diseño Electronico y Técnicas de Tratamiento de SeñalesÁrea de conocimiento
Arquitectura y Tecnología de ComputadorasPatrocinadores
This research is being funded by Ministerio de Ciencia y Tecnología TIC 2003-09557-C02-02.Fecha de publicación
2007-06-23Editorial
Springer BerlinCita bibliográfica
GARRIGÓS GUERRERO, Javier et al. HANNA: a tool for hardware prototyping and benchmarking of ANNs. En: International Work Conference on the Interplay between Natural and Artificial Computation . IWINAC 2007 (2ª: La Manga del Mar Menor, Murcia, Spain: 2007). Nature Inspired Problem-Solving Methods in Knowledge Engineering. Berlin: Springer, 2007. Pp. 10-18. ISBN 978-3-540-73054-5Palabras clave
Tecnologías VLSIArquitectura de hardware
HANNA (Hardware ANN Architect)
Artificial neural networks
Resumen
For some applications, designers must implement an ANN model over different
platforms to meet performance, cost or power constrains, a process still more
painful when several hardware implementations have to be evaluated. Continuous
advances in VLSI technologies, computer architecture and software development
make it difficult to find the adequate implementation platform. HANNA (Hardware
ANN Architect), is a tool designed to automate the generation of hardware
prototypes of MLP-like neural networks over FPGA devices. Coupled with
traditional Matlab/Simulink environments the model can be synthesized,
downloaded to the FPGA and co-simulated with the software version to trade off
area, speed and precision requirements.
Colecciones
El ítem tiene asociados los siguientes ficheros de licencia:
Redes sociales