convert the weight s of neural from float "double" to fixed ponit

hi

i try to convert the weights of my neural networks from float point "double" to

2'complement fixed point representation with 2 bit for real and 14 bit for

fraction so can i use them in my FPGA

what is the best fun that do this work in matlab??

and what is rounding method that this fun use

thank in advance

s.s

Answer 1

Maybe this is helpful?

http://www.mathworks.com/matlabcentral/fileexchange/5485-twos-complement-for-matlab

i try to use matlab function not any function