Convolutional Neural Networks (CNN) is a class of Feedforward Neural Networks that contain convolutional computation and have deep structure, and is one of the representative algorithms of deep learning. It is one of the representative algorithms of deep learning.
Research on convolutional neural networks began in the 1980s and 1990s, and time-delay networks and LeNet-5 were the first convolutional neural networks to appear; after the twenty-first century, with the proposal of deep learning theory and the improvement of numerical computation equipment, convolutional neural networks have been developed rapidly, and have been applied to computer vision, natural language processing and other fields. The field.
Properties
The connection between the convolutional layers in a convolutional neural network is called a sparse connection, which means that the neurons in a convolutional layer are connected to only part of their neighboring layers, not all of them, compared to the full connection in a feed-forward neural network. Specifically, any pixel (neuron) in the feature map of layer l of the convolutional neural network is only a linear combination of pixels within the receptive field defined by the convolutional kernel in layer l-1.
The sparse connections of convolutional neural networks have the effect of regularization, which improves the stability and generalization ability of the network structure and avoids overfitting, and at the same time, the sparse connections reduce the total number of weight parameters, which is conducive to the fast learning of neural networks, and the reduction of the memory overhead during the computation.