Exploring the Integration of Neural Networks in Quality-Oriented Education for Undergraduates: Evolutionary Computing-Based Personalized Learning Path Recommendation

This study will explore the design, implementation, and evaluation of a neural network-based recommendation system that suggests learning resources tailored to the unique requirements of undergraduate students. We use a convolutional neural network to extract meaningful features from the input data, representing the characteristics of each student. This paper proposes to combine a knowledge graph, deep knowledge tracking model, and ant colony algorithm and improve the traditional ant colony algorithm by classifying ant colonies. First, the key concepts knowledge graph is abstracted as the path basis. Deep knowledge tracking is applied to classify learners at different levels, and the difficulty weight is combined. Then, the ant colony algorithm is used to carry out the corresponding path planning, and the ant colony is divided according to different learner categories, ensuring the relatively shortest learning path and considering the objective knowledge level of different learning groups to obtain personalized and efficient learning path recommendations. Finally, the ASSISTments dataset is used to verify the effectiveness of the proposed method. Integrating an evolutionary computing-based personalized learning path recommendation approach holds significant promise in augmenting quality-oriented education for undergraduate students. This approach fosters personalized learning experiences, optimizes the allocation of educational resources, enhances learning outcomes, and offers precise and comprehensive recommendations for learning paths. By harnessing advanced computational methodologies, this approach empowers educators to provide a superlative educational environment that accommodates each student’s unique requirements and learning objectives.