|
| << vorige | volgende >> |
Tijdschrift beschrijving
Alle jaargangen van het bijbehorende tijdschrift
Alle afleveringen van het bijbehorende jaargang
Alle artikelen van de bijbehorende aflevering
Details van artikel 16 van 32 gevonden artikelen
| Titel: |
Direct Exponential Function Computer in Neural Network Application Based on Evolvable Hardware |
| Auteur: |
Z. Huajun Z. Jin |
| Verschenen in: |
Information technology journal |
| Paginering: | Jaargang 7 (2008) nr. 8 pagina's 1156-1162 |
| Jaar: |
2008 |
| Inhoud: |
This study proposes a new direct exponential function computer based on CORDIC algorithm to solve the neuron realization problem on the Evolvable Hardware (EHW). The direct exponential function computer combines the essential character of exponential function with CORDIC algorithm and turns aside the conventional approach which computes the exponential function by adding sinh (x) and cosh (x) indirectly. Because the direct computer executes shift-add operation in allusion to exponential function directly and get rid of the computation of sinh (x) and cosh (x), it not only calculates much faster than the indirect computer, but also saves much more logic gates. In addition, through strict and integrated analysis, the direct computer is proved to own perfect convergence. It converges to the real value with arbitrary precision and operates shift-add operation without any unnecessary rotation. Since of the direct efficient shift-add operation, the direct computer is useful for the application of neural network based on the EHW. |
| Uitgever: |
Asian Network for Scientific Information, Pakistan (provided by DOAJ) |
| Bronbestand: |
Elektronische Wetenschappelijke Tijdschriften |
Details van artikel 16 van 32 gevonden artikelen
| << vorige | volgende >> |