Samal RESEARCH AND ANALYSIS OF THE NEURAL NETWORK IMPLEMENTATION IN TEACHING PHYSICS IN HIGHER EDUCATION

Abstract

Implementing innovative technologies is a key factor in improving the quality of education in the contemporary educational process. The research aims to research and analyze the implementation of neural networks in teaching physics in higher education. The main focus is on analyzing the efficiency and potential benefits of using contemporary artificial intelligence (AI) technologies for improving the learning process. Various approaches were used in the study to employ neural networks to create adaptive educational systems, personalized training programs, and virtual laboratories. Particular emphasis was given to the effects of these technologies on students’ academic performance, involvement in the learning process, and comprehension of complex physical concepts. The research methodology includes a review of existing literature, experiments using neural networks in the teaching process, and a survey taken from students and teaching staff. During the experiments, various neural network models, namely recurrent neural networks (RNN) and deep neural networks (DNN), are employed to tackle issues in predicting academic performance, personalized education, and automatically generating training materials. The research results reveal that implementing neural networks in teaching physics can significantly raise the teaching quality, foster a tailored approach to each student, and facilitate the teachers’ routine tasks. Moreover, AI can stimulate students’ interest in learning physics and related disciplines due to its interactivity and adaptability in the educational process. Implementing neural networks in teaching physics in higher education offers a promising direction, which requires further study and development.