Practical Neural Network Recipies in C++

Appendix

453

copy weights - Copy the weights from one network to another

Note that this 1s NOT like a copy or assignment.

as 1t does not copy other parameters. In fact.

1t gets sizes from the calling Instance!

*/

void KohNet::copy weights ( KohNet *dest . KohNet *source )

{

1nt n ;

dest->neterr - source->neterr ;

1f (source->exe && dest->exe) // These may be Important too!

memcpy ( dest->confuslon . source->confusi on . (nout+1) * slzeofdnt) )

n - nout * (n1n+l) ;

memcpy ( dest->out coefs . source->out coefs . n * s1zeof(doubl

e)

) ;

zero weights - Zero all weights 1n a network

void KohNet::zero weights ()

{

1nt n ;

neterr —1.0 ;

n - nout * ...