Convolution and Deep Learning

"Convolution is probably the most important concept in deep learning  ... You can imagine convolution as the mixing of information..."

"There can be a lot of distracting information in images that is not relevant to what we are trying to achieve ... the shape of a blouse is very different from the shape of a shirt, jacket, or trouser. So if we could filter the unnecessary information out of images then our algorithm will not be distracted by the unnecessary details like color and branded emblems. We can achieve this easily by convoluting images with kernels."

"Instead of having fixed numbers in our kernel, we assign parameters to these kernels which will be trained on the data. As we train our convolutional net, the kernel will get better and better at filtering a given image (or a given feature map) for relevant information. This process is automatic and is called feature learning."

"A quantum algorithm would be able to calculate all possible combinations described by the kernel with one computation and in linear time/qubits with respect to the size of image and kernel."

"Fourier transforms contain a lot of information about orientation of an image"

"With the powerful convolution theorem we then developed an interpretation of convolution as the diffusion of information across pixels."

https://timdettmers.com/2015/03/26/convolution-deep-learning/

#Convolution #deepLearning