Title :
Optimizing FPGA implementation of Feed-Forward Neural Networks
Author :
Oniga, S. ; Tisan, A. ; Mic, D. ; Buchman, A. ; Vida-Ratiu, A.
Author_Institution :
Dept. of Electron. & Comput. Eng., North Univ., Baia Mare
Abstract :
This paper presents an in depth study of FPGA implementation of feed-forward neural networks regarding error reduction as a function of number of bits used for weights representation. Xilinx block parameters influence on resources occupied by network and the maximum working frequency is also studied.
Keywords :
circuit optimisation; feedforward neural nets; field programmable gate arrays; neural chips; Xilinx block parameters; feed-forward neural networks; maximum working frequency; optimizing FPGA implementation; weights representation; Artificial neural networks; Equations; Feedforward neural networks; Feedforward systems; Field programmable gate arrays; Hardware; Neural networks; Neurons; Parallel processing; Random access memory;
Conference_Titel :
Optimization of Electrical and Electronic Equipment, 2008. OPTIM 2008. 11th International Conference on
Conference_Location :
Brasov
Print_ISBN :
978-1-4244-1544-1
Electronic_ISBN :
978-1-4244-1545-8
DOI :
10.1109/OPTIM.2008.4602494
