The Study for Convolutional Neural Network and Corresponding Applications

Abstract

Deep learning is a key technological tool in the field of image identification with wide application prospects because of its significant benefits in feature extraction and model fitting. Deep learning entails numerous stages of non-linear transformations. The primary implementation of the current deep learning technique is the deep neural network, the connection pattern of which takes its reference from the way that the visual cortex of animals is organized. Among all the deep learning methods, Convolutional Neural Network (CNN) is one of the most renowned means to process image. It has excellent performance in terms of large-scale image processing. A convolutional neural network consists of convolutional layers, a fully connected layer, a pooling layer, and associated weights. Convolutional neural networks have fewer parameters to consider than other deep, feed forward neural networks, making them an attractive deep learning architecture. There are several traits in CNN, including pooling, shared weights, and local connections. With the help of these features, the network's complexity and the quantity of training parameters can be decreased, and the model's level of invariance to scale, shift, and distortion can be increased, along with its robustness and fault tolerance. This paper firstly summarized the history of convolutional neural network, then briefly discussed the components like the neuron and multilayer perception. The main structure of the CNN is showed afterwards. The paper also mentioned the features and the applications of CNN, mainly in the field of Computer Vision (CV).