A Deep Neural Networks-Based Research Method for Investigating the Mechanisms of Educational Resource Equalization

With technological advancements, particularly in artificial intelligence, the application of Deep Neural Networks (DNN) technologies for optimizing educational resources has become increasingly feasible. The gap in educational resources is a significant global issue, affecting students' learning outcomes and future opportunities. This study aims to explore the mechanisms and effects of applying DNN techniques to narrow the gap in educational resources for the development of sustainable education. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) were utilized to analyze the usage of educational resources and students' learning data. A controlled experiment was designed to compare the resource utilization efficiency and academic performance between the experimental group (using DNN technology) and the control group (using traditional resource allocation methods). The research found that DNN technology significantly enhanced the efficiency of educational resource distribution, particularly in resource-limited environments, by more accurately predicting and meeting students' learning needs. The academic performance and satisfaction of students in the experimental group improved markedly. DNN technology demonstrates substantial potential in the allocation of educational resources, offering new possibilities and directions for narrowing the gap in educational resources.