Open lingtengqiu opened 3 years ago
the complete logic is:
as for your derivation, I don't get how can you get "var[sin(30Wx+b)]"... note that there is a sine... normally, you cannot directly get the variance computed unless you know it is an arcsine distribution. and note that 30 plays a role in make that arcsine as well..
I am confused about first_layer_sine_init, where you set W~uniform(-1/n,1/n).
As we know, input is X-uniform(-1,1) so has var[x] = (2^2/12)=1/3. and after FC layer, var[sin(30Wx+b)] = 30^2n(1/3)(c^2/3) =1? so how you initialize first-layer-weight by uniform(-1/n,1/n)?