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

<p>Aiming at the problem that it is difficult to objectively analyze the degree of teaching based on teaching materials in the traditional way, this paper establishes an index system based on the opinions of experts and the characteristics of teaching based on teaching materials. A BP neural network analyzes the index system to measure the level of teaching by university teachers based on teaching materials. This paper aims to improve the running speed of the BP neural network by employing the gradient-at-every-turn method and optimizing parameters. Moreover, the maximum-minimum value method is used to normalize the data, and the entropy value method is used to calculate the weights of the indicators to provide more accurate data for the BP neural network. Once the model construction was finished, it was put through its paces in teacher training and science colleges for trial operation. The absolute value difference between the output of the neural network and the expert evaluation is between 0.09 and 0.052, which are all less than 0.1. Most of the teachers’ scores are at the excellent level, around 0.8-0.9, but the score for diversified teaching methods is 0.6784, which is on the low side, proving that there is still room for improvement in this aspect.</p>
</abstract>

Aiming at the problem that it is difficult to objectively analyze the degree of teaching based on teaching materials in the traditional way, this paper establishes an index system based on the opinions of experts and the characteristics of teaching based on teaching materials. A BP neural network analyzes the index system to measure the level of teaching by university teachers based on teaching materials. This paper aims to improve the running speed of the BP neural network by employing the gradient-at-every-turn method and optimizing parameters. Moreover, the maximum-minimum value method is used to normalize the data, and the entropy value method is used to calculate the weights of the indicators to provide more accurate data for the BP neural network. Once the model construction was finished, it was put through its paces in teacher training and science colleges for trial operation. The absolute value difference between the output of the neural network and the expert evaluation is between 0.09 and 0.052, which are all less than 0.1. Most of the teachers’ scores are at the excellent level, around 0.8-0.9, but the score for diversified teaching methods is 0.6784, which is on the low side, proving that there is still room for improvement in this aspect.

Analysis of the Professionalism of College Teachers in the Information Age Based on Teaching According to Materials

Applied Mathematics and Nonlinear Sciences

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

Aiming at the problem that it is difficult to objectively analyze the degree of teaching based on teaching materials in the traditional way, this paper...

Analysis of the Professionalism of College Teachers in the Information Age Based on Teaching According to Materials

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 18. Dez. 2023

Akzeptiert: 26. Dez. 2023

DOI: https://doi.org/10.2478/amns-2024-0184

Schlüsselwörter
BP neural network, Common gradient method, Data normalization, Entropy value method, Tailored instruction

© 2024 Xiaojing Qiang, published by Sciendo

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

Analysis of the Professionalism of College Teachers in the Information Age Based on Teaching According to Materials

Online veröffentlicht: 31. Jan. 2024

Seitenbereich: -

Eingereicht: 18. Dez. 2023

Akzeptiert: 26. Dez. 2023

DOI: https://doi.org/10.2478/amns-2024-0184

SchlüsselwörterBP neural network, Common gradient method, Data normalization, Entropy value method, Tailored instruction

© 2024 Xiaojing Qiang, published by Sciendo

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

Schlüsselwörter
BP neural network, Common gradient method, Data normalization, Entropy value method, Tailored instruction