Introduction
Convolution neural networks (CNN) are a category of deep learning neural networks with a prominent role in building image recognition- and natural language processing-based classification models.
Note
The CNN follows a similar architecture to LeNet, which was primarily designed to recognize characters such as numbers, zip codes, and so on. As against artificial neural networks, CNN have layers of neurons arranged in three-dimensional space (width, depth, and height). Each layer transforms a two-dimensional image into a three-dimensional input volume, which is then transformed into a three-dimensional output volume using neuron activation.
Primarily, CNNs are built using three main types of activation layers: convolution layer ReLU, pooling layer, and fully connected layer. The convolution layer is used to extract features (spatial relationship between pixels) from the input vector (of images) and stores them for further processing after computing a dot product with weights (and...
