Your search for: 'author:("Wang, Yuzhe")' has returned 2 results. (0.008s) Save search

Authors: Wang, Yuzhe

Article Type: Research Article

Abstract: As an inevitable trend in the development of English teaching, English distance education needs to use artificial intelligence to control the classroom, so as to improve the degree of control of teacher over the classroom. Based on the machine learning algorithm, according to the needs of English distance education classroom management, this paper builds an English distance education classroom management system based on improved machine learning artificial intelligence algorithms. Moreover, this research constructs the system function module through requirement analysis, and combines the positioning algorithm to locate students in real time. In addition, this study analyzes the students’ status through …intelligent database processing to grasp the students’ learning status in a timely and effective manner. In order to verify the performance of this system, this study verifies the performance of the model by means of comparative experiments. The research results show that the system constructed in this paper has a certain effect. Show more

Keywords: Artificial intelligence, machine learning, improved algorithms, English education, classroom management

DOI: 10.3233/JIFS-189385

Citation: Journal of Intelligent & Fuzzy Systems, vol. 40, no. 2, pp. 3477-3488, 2021

Authors: Li, Ping | Wang, Yuzhe | Wu, Cong | Kang, Xiatao

Article Type: Research Article

Abstract: Pruning of neural networks is undoubtedly a popular approach to cope with the current compression of large-scale, high-cost network models. However, most of the existing methods require a high level of human-regulated pruning criteria, which requires a lot of human effort to figure out a reasonable pruning strength. One of the main reasons is that there are different levels of sensitivity distribution in the network. Our main goal is to discover compression methods that adapt to this distribution to avoid deep architectural damage to the network due to unnecessary pruning. In this paper, we propose a filter texture distribution that …affects the training of the network. We also analyze the sensitivity of each of the diverse states of this distribution. To do so, we first use a multidimensional penalty method that can analyze the potential sensitivity based on this texture distribution to obtain a pruning-friendly sparse environment. Then, we set up a lightweight dynamic threshold container in order to prune the sparse network. By providing each filter with a suitable threshold for that filter at a low cost, a massive reduction in the number of parameters is achieved without affecting the contribution of certain pruning-sensitive layers to the network as a whole. In the final experiments, our two methods adapted to texture distribution were applied to ResNet Deep Neural Network (DNN) and VGG-16, which were deployed on the classical CIFAR-10/100 and ImageNet datasets with excellent results in order to facilitate comparison with good cutting-edge pruning methods. Code is available at https://github.com/wangyuzhe27/CDP-and-DTC . Show more

Keywords: Threshold, neural network, penalty, pruning

DOI: 10.3233/AIC-230046

Citation: AI Communications, vol. 36, no. 4, pp. 311-323, 2023