Learning-from-data

Learning-from-data copied to clipboard

Hi. Why you assume that $\theta'(s^{(l)}_j)=1$ for all $\delta^{(2)}$ and $\delta^{(1)}$? We have identity output only for the final layer, all previous layers use $tanh(x)$ transformation. So, we calculate $\delta^{(2)}$...

sharov-am