Design and implementation of a single layer feed forward neural network using stand-alone architecture FPGAs-based platform

Abstract EN

A single layer feed-forward neural network are proposed and implemented using the schematic editor of the Xilinx foundation series 2.1i.

First the mathematical model of the data set (weights and inputs) is presented in a matrix multiplication format.

Secondly the five design stages are presented and implemented without using the finite state machine, which control the processes of the forward propagation phase, error calculation, and the training algorithm.

Finally the design can be optimized to decrease the total execution time and to minimize the cost, which eventually will increase the performance and improve the function density.