In this video you will learn about:
A CNN is a type of NN where we apply convolutional layers to our net usually to extract visual features. We can make a CNN architecture in many ways, they are similar to ordinary NN because they are made up of learnable weights (convolution kernels) and biases.
Now, look at the specific one layer. Notice the sliding kernel. Also notice that, even though it's not obvious on first sight, the dimensionality of the projected matrix (matrix on the right) is lower then the matrix (the input matrix on the left) upon which the kernel is sliding on. You can observe that that the edges of the later "A" are closer to the edges on the projected matrix than they are on the input matrix.
In 2012, Alex Krizhevsky in collaboration with Ilya Sutskever and Geoffrey Hinton developed a CNN called AlexNet. It was a revolution in CV. The model became an inspiration for future state-od-the-art works!