A Convolutional neural network (CNN, or ConvNet) is another type of neural network that can be used to enable machines to visualize things.
CNN’s are used to perform analysis on images and visuals. These classes of neural networks can input a multi-channel image and work on it easily with minimal preprocessing required.
These neural networks are widely used in:
- Image recognition and Image classification
- Object detection
- Recognition of faces, etc.
Therefore, CNN takes an image as an input, processes it, and classifies it under certain categories.
Image Source: Google Images
Convolution is the process of convolving a kernel with an image (sum of multiplication of corresponding pixels in the kernel and image). The kernel operates over the whole image. You can find lots of information online regarding this technique if I wasn’t descriptive enough.
A convolutional neural network is a neural network, where the input is an image and convolutions with various kernels occur in each layer to produce the convolved image as the input into the next layers. There are often other types of layers in better convolutional layers such as pooling layers that extract the important information/features from the previous layer’s convolutions.