Abstract
The rapid advancement of artificial intelligence (AI) offers new opportunities to enhance teaching and learning in early education. This study applies deep learning approaches to support early cognitive development among primary students in an Indonesian Islamic school. A hybrid Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) model was designed to analyse students’ cognitive patterns, attention, and engagement. Using a mixed-methods design, the research involved 60 students aged 8–10 at MIS Terpadu Alhijrah Bintuju. The model processed multimodal classroom data to generate adaptive feedback and personalized learning pathways. Results showed significant improvements in attention (+18%), memory recall (+22%), and problem-solving (+25%) after eight weeks of AI-assisted learning. Qualitative findings revealed higher motivation, engagement, and self-regulation. The study demonstrates that culturally aligned AI systems can effectively enhance early cognitive development and promote learner autonomy in Islamic primary education.
