Low Cost Hardware Back Propagation Algorithm
The first successful implementation of Artificial Neural Networks (ANNs) was published a little over a decade ago. It is time to review the progress that has been made in this research area. This paper provides taxonomy for classifying Field Programmable Gate Arrays (FPGAs) implementation of ANNs. D...
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Al-Khwarizmi College of Engineering – University of Baghdad
2007
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/cc163f6fc02f4850885e861cb0298b82 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | The first successful implementation of Artificial Neural Networks (ANNs) was published a little over a decade ago. It is time to review the progress that has been made in this research area. This paper provides taxonomy for classifying Field Programmable Gate Arrays (FPGAs) implementation of ANNs. Different implementation techniques and design issues are discussed, such as obtaining a suitable activation function and numerical truncation technique trade-off, the improvement of the learning algorithm to reduce the cost of neuron and in result the total cost and the total speed of the complete ANN. Finally, the implementation of a complete very fast circuit for the pattern of English Digit Numbers NN has four layers of 70 nodes (neurons) on single chip using Xilinx FPGA technique is given.The main goal of this paper is how to achieve the suitable activation function and weights for this network that gives minimum hardware cost when all stages of this ANN algorithm is implemented on FPGA |
|---|