Convolutional Neural Network (CNN) is a special kind of feed-forward neural network that includes convolutional and pooling layers in its architecture. Also known as ConvNets, the general pattern for the CNN architecture is to have these layers in the following sequence:
- Fully connected input layer
- Multiple combinations of convolutional, pooling, and fully connected layers
- Fully connected output layer with softmax activation
CNN architectures have proven to be highly successful in solving problems that involve learning from images, such as image recognition and object identification.
In this chapter, we shall learn the following topics related to ConvNets:
- Understanding Convolution
- Understanding Pooling
- CNN architecture pattern-LeNet
- LeNet for MNIST dataset
- LeNet for MNIST with TensorFlow
- LeNet for MNIST with Keras
- LeNet for CIFAR dataset
- LeNet...
