<abstract xmlns="http://www.w3.org/1999/xhtml">
<p>To better improve students’ physical quality, this paper constructs a self-coding training model for the optimal path of football physical education based on the self-coding neural network in the deep learning model. The student’s physical performance and teaching methods are input into the self-coding neural network for the optimal path of football physical education as the input layer. The data are corrected by regularizing and balancing the data in the input layer through coding and decoding in the implicit layer. The corrected data is reconstructed and transformed as the input layer of the next level of the self-coding neural network. The above steps are repeated until the same output layer parameters as the pre-trained model are reached, resulting in the optimization path of football physical education teaching: changing the teaching mode and improving the teaching ability of teachers. The simulation results show that the optimized teaching mode can improve the average score of students’ football physical education by 33 points. Taking junior students as an example, after the teacher’s teaching ability was improved, the excellent rate of students’ football physical education scores increased from 7% to 29%. From the above results, it can be seen that the optimized path of football physical education based on the deep learning model is feasible and can improve students’ physical quality.</p>
</abstract>

To better improve students’ physical quality, this paper constructs a self-coding training model for the optimal path of football physical education based on the self-coding neural network in the deep learning model. The student’s physical performance and teaching methods are input into the self-coding neural network for the optimal path of football physical education as the input layer. The data are corrected by regularizing and balancing the data in the input layer through coding and decoding in the implicit layer. The corrected data is reconstructed and transformed as the input layer of the next level of the self-coding neural network. The above steps are repeated until the same output layer parameters as the pre-trained model are reached, resulting in the optimization path of football physical education teaching: changing the teaching mode and improving the teaching ability of teachers. The simulation results show that the optimized teaching mode can improve the average score of students’ football physical education by 33 points. Taking junior students as an example, after the teacher’s teaching ability was improved, the excellent rate of students’ football physical education scores increased from 7% to 29%. From the above results, it can be seen that the optimized path of football physical education based on the deep learning model is feasible and can improve students’ physical quality.

Esearch on the optimization path of campus football teaching based on deep learning mode

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

To better improve students’ physical quality, this paper constructs a self-coding training model for the optimal path of football physical education based on...

Esearch on the optimization path of campus football teaching based on deep learning mode

Publié en ligne: 29 juil. 2023

Pages: -

Reçu: 09 oct. 2022

Accepté: 06 févr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00107

Mots clés
Deep learning models, Self-coding neural networks, Regularized equilibrium processing, Reconfiguration transformations, Teaching optimization paths, football physical education

© 2023 Hong Zou, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Esearch on the optimization path of campus football teaching based on deep learning mode

Publié en ligne: 29 juil. 2023

Pages: -

Reçu: 09 oct. 2022

Accepté: 06 févr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00107

Mots clésDeep learning models, Self-coding neural networks, Regularized equilibrium processing, Reconfiguration transformations, Teaching optimization paths, football physical education

© 2023 Hong Zou, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Mots clés
Deep learning models, Self-coding neural networks, Regularized equilibrium processing, Reconfiguration transformations, Teaching optimization paths, football physical education