Principle of Convolutional Neural Network

Convolutional neural network (CNN) is a kind of feed-forward neural network, inspired by the natural visual cognitive mechanism of living creatures. Nowadays, CNN has become one of the research hotspots in many scientific fields, especially in the field of pattern classification, because the network avoids the complex pre-processing of the image, and can be directly inputted into the original image, and thus has been more widely used. It can be applied to image classification, target recognition, target detection, semantic segmentation and so on. The basic structure of convolutional neural network for image classification.

1. Definition

Convolutional Neural Networks (CNN) is a class of Feedforward Neural Networks (FNNs) that contains convolutional computation and has a deep structure, and is one of the representative algorithms of deep learning. It is one of the representative algorithms of deep learning. Convolutional neural networks have the ability of representation learning and can perform shift-invariant classification of input information according to their hierarchical structure, so they are also called "Shift-invariant Artificial Neural Networks" (SINNs). Invariant Artificial Neural Networks (SIANN)".

2. Characteristics

In contrast to the previously described neural networks, which have only linear connections, CNNs include **convolution** operations, **pooling operations, and nonlinear activation function mapping (i.e., linear connections)**, among others.

3. Applications and Typical Networks

Classical CNN networks:

Alex-Net

VGG-Nets

Resnet

Common applications:

Deep Learning has been used with great success in computer image recognition. Using deep learning, we are able to recognize images with high accuracy, and to achieve this, we rely heavily on a branch of neural networks called convolutional networks