مشاركة الاوزان في convolutional layer يسمح لنا من استغلال ترابط pixels مع بعضها البعض.
Or is it just an empirical way? The convolution of another filter with the green outline , over the same image gives a different feature map as shown.
I am confused about this.
Note that in Figure 15 below, since the input image is a boat, the target probability is 1 for Boat class and 0 for other three classes, i.