Optimization of neural network models for personalization of educational processes: comparison of methods and variability analysis of architectures

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Comparison of neural network models and machine learning methods improves predictions of learning outcomes.

Personalized educational processes improve learning outcomes by utilizing optimized neural network models.
Multinomial regression and ensemble methods like random forests were compared in terms of predictive accuracy.
Analysis of neural network architectures revealed influences of hidden layer neuron count on model performance.
Implementation may enhance adaptive educational platforms, allowing for dynamic curriculum adjustments.

Anton Cherepkov (2025) studied this question.

View Full Paper

Ask AI

Bookmark