<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In this paper, we utilize deep learning methods to perform automatic feature learning from multi-source heterogeneous data, mapping different data into the same hidden space, and obtaining the deep features of the data associated with students and sports. A small amount of information is filtered from a large amount of input information by assigning weights in the attention mechanism and higher weights are assigned to it, and a collaborative filtering recommendation algorithm based on deep learning and algorithm evaluation index is proposed. The deep learning algorithm is integrated into the classroom of “basketball one-handed in situ over-the-shoulder shooting” in college B for empirical analysis, and the teaching effect is compared with that of the traditional teaching mode. The results show that the average scores of 50 meters, sit-ups, pull-ups, 800 meters, 1,000 meters, seated forward bending, and cross-direction running of the students in the physical education classroom based on deep learning are higher than those of the students in the traditional physical education classroom by 5.94, 6.83, 7.69, 6.56, 5.87, 5.1, and 3.68 in the physical fitness comparison analysis. Study shows that physical education teaching based on deep learning can improve students’ various physical qualities, which is of great significance and value in accelerating the high-quality development of physical education and promoting students’ comprehensive development.</p>
</abstract>

In this paper, we utilize deep learning methods to perform automatic feature learning from multi-source heterogeneous data, mapping different data into the same hidden space, and obtaining the deep features of the data associated with students and sports. A small amount of information is filtered from a large amount of input information by assigning weights in the attention mechanism and higher weights are assigned to it, and a collaborative filtering recommendation algorithm based on deep learning and algorithm evaluation index is proposed. The deep learning algorithm is integrated into the classroom of “basketball one-handed in situ over-the-shoulder shooting” in college B for empirical analysis, and the teaching effect is compared with that of the traditional teaching mode. The results show that the average scores of 50 meters, sit-ups, pull-ups, 800 meters, 1,000 meters, seated forward bending, and cross-direction running of the students in the physical education classroom based on deep learning are higher than those of the students in the traditional physical education classroom by 5.94, 6.83, 7.69, 6.56, 5.87, 5.1, and 3.68 in the physical fitness comparison analysis. Study shows that physical education teaching based on deep learning can improve students’ various physical qualities, which is of great significance and value in accelerating the high-quality development of physical education and promoting students’ comprehensive development.

Research on Physical Education Teaching in Universities Based on Deep Learning

Ideological and Political Theory Teaching Department

Applied Mathematics and Nonlinear Sciences

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

{"article-title":"Research on Physical Education Teaching in Universities Based on Deep Learning"}

In this paper, we utilize deep learning methods to perform automatic feature learning from multi-source heterogeneous data, mapping different data into the...

Research on Physical Education Teaching in Universities Based on Deep Learning

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 02. Jan. 2024

Akzeptiert: 09. Jan. 2024

DOI: https://doi.org/10.2478/amns-2024-0319

Schlüsselwörter
Deep learning, Attention mechanism, Assigning weights, Collaborative filtering, Physical education

© 2024 Tao Wang, published by Sciendo

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

Research on Physical Education Teaching in Universities Based on Deep Learning

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 02. Jan. 2024

Akzeptiert: 09. Jan. 2024

DOI: https://doi.org/10.2478/amns-2024-0319

SchlüsselwörterDeep learning, Attention mechanism, Assigning weights, Collaborative filtering, Physical education

© 2024 Tao Wang, published by Sciendo

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

Schlüsselwörter
Deep learning, Attention mechanism, Assigning weights, Collaborative filtering, Physical education