Question

What kind of filter functions over receptive windows are convolutional layers learning?

Answer 1

Convolutional Neural Networks are (usually)  supervised methods for image/object recognition. This means that you need to train the CNN using a set of labelled images: this allows to optimize the weights of its convolutional filters, hence learning the filters shape themselsves, to minimize the error.

Once you have decided the size of the filters, as much as the initialization of the filters is important to "guide" the learning, you can indeed initialize them to random values, and let the learning do the work.

Enrico

Answer 2

Answer:

Touch and hold a clip to pin it. Unpinned clips will be deleted after 1 hour.{

Java Statement 2;

-----------------------

}

.

.

.

else

{

Java Statement n;

-----------------------

}