Programming a Reconfigurable Platform for Neural Network Simulations

S. Erdogan (USA)


Programming, reconfigurable hardware, neural networks,VHDL.


This paper describes the programming of a reconfigurable environment such an FPGA to handle neural network simulations. Typical application of the neural networks can be found in speech and image processing. The objective is to achieve a computational model that is reconfigurable not only in the domain of communications and control but also in the domain of processing. The key to the performance of the model is a fast floating-point sum of products circuit using special carry-save multipliers and extensive pipelining. VHDL description of the model has been used for simulation, synthesis and optimization for mapping to XILINX FPGA technology.

Important Links:

Go Back