Deep learning model-based reading of Chinese language and literature classics and situational experience

• Published in: Applied mathematics and nonlinear sciences Vol. 9; no. 1
• Main Author: Chen, Lu
• Format: Journal Article
• Language: English
• Published: Sciendo 01-01-2024
• Subjects: 97C50; Boltzmann machine; Deep learning algorithm; Energy function; Neuron nodes; Situated experience model
• ISSN: 2444-8656; 2444-8656
• DOI: 10.2478/amns.2023.2.00521

In this paper, a new media scenario experience model is constructed to integrate Chinese language and literature works through deep learning algorithms. Firstly, the model is trained as a whole, RBM is a special form of Boltzmann machine, and the energy function is defined by combining the input layer vector and the hidden layer vector to calculate the marginal probability distribution. Then the defined energy function can be used to derive the joint probability formula of state values, link this probability formula with the hidden layer between the neuron nodes, use the logistic function to define the energy of the whole Boltzmann machine, and finally, after repeated training to derive the entropy function of the RBM, to complete the construction of a new media-based scenario experience platform. The experimental results show that after a semester of teaching based on this platform, the scoring examination of new media scenario experience classical reading was conducted. The percentage of those who passed was 82%, and only 18% failed. Therefore, we should make full use of multimedia technology, innovate efficient Chinese language and literature teaching methods, turn the classroom into a stage, enhance the novelty of Chinese language and literature courses, and enhance the intuitiveness of classical reading in Chinese language and literature.