We had mentioned three main terminologies related to the CNN architecture:
- Convolutions
- Pooling
- Feature Maps
In this and the next few segments, we will go through each one of them in detail. Let’s start by understanding how convolutions work.
Convolution
Mathematically, the convolution operation is the summation of the element-wise product of two matrices. Let’s take two matrices, X and Y. If you ‘convolve the image X using the filter Y’, this operation will produce the matrix Z.
Finally, you compute the sum of all the elements in Z to get a scalar number, i.e. 3+4+0+6+0+0+0+45+2 = 60.
In the next segment, you will build on your newly acquired understanding of convolutions.
Report an error