سال انتشار: ۱۳۸۲

محل انتشار: یازدهمین کنفرانس مهندسی برق

تعداد صفحات: ۶

نویسنده(ها):

Gilberto Contreras, – Dept. of Electrical and Computer Engineering, The University of Texas at El Paso
Patricia Nava –
Faridoon Shabani –

چکیده:

Specialized hardware implementations of Artificial Neural Networks (ANNs) can offer faster execution than general-purpose microprocessors by taking advantage of reusable modules, parallel processes and specialized computational components. Modern high-density FPGAs offer the required flexibility and fast design-to-implementation time with the possibility of exploitinghighly parallel computations like those required by ANNs in hardware. This paper presents a fast digital ANN implemented in a Xilinx FPGA Spartan II device with performance of 150×106 connections per second (CPS