CNNs are the most prominent architectures that are used when working on images. CNNs address the major limitations of deep neural networks that we saw in the previous section. Besides image classification, they also help with object detection, image segmentation, GANs, and many more – essentially, wherever we use images. Furthermore, there are different ways of constructing a convolutional neural network, and there are multiple pre-trained models that leverage CNNs to perform various tasks. Starting with this chapter, we will be using CNNs extensively.
In the upcoming subsections, we will understand the fundamental building blocks of a CNN, which are as follows:
- Convolutions
- Filters
- Strides and padding
- Pooling
Let's get started!
Convolution
A convolution is basically multiplication between two matrices. As you saw in the previous chapter, matrix multiplication is a key ingredient of training a neural network. (We perform matrix multiplication when...
