Marina Anone
Institut Agama Kristen Negeri Kupang

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Application Of Deep Learning Model In Improving Early Childhood Development Meyzia Susang; Yelsi Benu; Rosalia Blegur; Marina Anone; Sarita Natumnea; Selvi Wahi; Fredericksen Victoranto Amseke
Jurnal E-MAS (Edukasi dan Pembelajaran Anak Usia Dini) Vol. 2 No. 2 (2026)
Publisher : FKIP UNSULTRA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64690/e-mas.v2i2.839

Abstract

Background: Cognitive development is an essential aspect of early childhood education as it underpins children’s abilities in thinking, reasoning, problem-solving, and decision-making that support lifelong learning. The Deep Learning model, which integrates mindful, meaningful, and joyful learning principles, is an innovative approach designed to enhance children’s engagement and learning experiences. However, empirical evidence on its effectiveness in relation to cognitive development in real kindergarten settings remains limited. Objective: This study aimed to analyze the relationship between the implementation of the Deep Learning model and the cognitive development of children aged 4–6 years at Cemara Liliba Kindergarten, Kupang City. Method: This quantitative study used an ex post facto design involving 20 children selected through purposive sampling. Data were collected through observation, interviews, documentation, and cognitive development assessments, then analyzed using descriptive statistics and simple linear regression with SPSS. Results: The findings indicated that the Deep Learning model encouraged active participation, curiosity, and enjoyable learning experiences among children through mindful, meaningful, and joyful activities. However, the regression analysis showed that the relationship between the Deep Learning model and cognitive development was not statistically significant (p > 0.05). The coefficient of determination (R² = 0.088) revealed that only 8.8% of cognitive development variance was explained by the model, while 91.2% was influenced by other factors. Novelty: This study provides empirical evidence of Deep Learning implementation in early childhood classrooms using an ex post facto design. Conclusion: The Deep Learning model created positive learning experiences but did not significantly affect children’s cognitive development.