convolution

Dilated convolution, is also known as Atrous Convolution or convolution with holes. The idea behind dilated convolution is to "inflate" the kernel which in turn skips some of the points. We can see the difference in the general formula and some visualization.

In MobileNet architecture, you must have stumbled across the term "Separable convolution". What is separable convolution and how is it different from regular convolution? We have explained everything in this article.

Convolutional Layer is the most important layer in a Machine Learning model where the important features from the input are extracted and where most of the computational time (>=70% of the total inference time) is spent. Concepts involved are kernel size, padding, feature map and strides