Search

With the increased demand for English translators in recent years, more scholars and researchers have begun to focus on college English translation education. The demand for computers to perform automatic natural language translation is at an all-time high, presenting another potential for machine translation (MT) research. Although neural machine translation (NMT) technology has advanced significantly, it still has several flaws. The reply NN-based MT technology is not optimal in the field of long sentence translation, and there are situations such as missing translation and overtranslation. So this paper proposes college English translation based on a convolutional neural network (CNN). This paper proposes that CNNs have stronger feature extraction and information processing capabilities than other deep NNs. It successfully solves the situation of missing translation and overtranslation, lowering the quality of college English translation instruction. The experimental results of this research reveal that when the length of an English sentence grows longer, the translation accuracy based on the reply NN drops to 47.9%, while the translation accuracy based on the CNN is 89.7%. It can be seen that college English translation based on CNN can be integrated into English translation teaching as an innovation of traditional teaching methods, so as to create a learning environment for students and enhance learning effects. MT based on CNN has greatly improved students' performance, which is conducive to improving the quality of college English translation teaching. [ABSTRACT FROM AUTHOR]

Nowadays, the information processing capabilities and resource storage capabilities of computers have been greatly improved, which also provides support for the neural network technology. Convolutional neural networks have good characterization capabilities in computer vision tasks, such as image recognition technology. Aiming at the problem of high similarity image recognition and classification in a specific field, this paper proposes a high similarity image recognition and classification algorithm fused with convolutional neural networks. First, we extract the image texture features, train different types, and different resolution image sets and determine the optimal texture different parameter values. Second, we decompose the image into subimages according to the texture difference, extract the energy features of each subimage, and perform classification. Then, the input image feature vector is converted into a one-dimensional vector through the alternating 5-layer convolution and 3-layer pooling of convolutional neural networks. On this basis, different sizes of convolution kernels are used to extract different convolutions of the image features, and then use convolution to achieve the feature fusion of different dimensional convolutions. Finally, through the increase in the number of training and the increase in the amount of data, the network parameters are continuously optimized to improve the classification accuracy in the training set and in the test set. The actual accuracy of the weights is verified, and the convolutional neural network model with the highest classification accuracy is obtained. In the experiment, two image data sets of gems and apples are selected as the experimental data to classify and identify gems and determine the origin of apples. The experimental results show that the average identification accuracy of the algorithm is more than 90%. [ABSTRACT FROM AUTHOR]