How the filter values are initialized by Convolution2D in keras.layes? Is it random?
While backpropogation, are filter values also updated along with weights in MLP.
Filter Values and backward propogation
Hey @preetishvij, weights in convolution 2D are initialized randomly only, following a certain distribution.
Yes while backpropagation these filter values are updated.
Hope this resolved your doubt.
Plz mark it as resolved in my doubts section. 