Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Educatio Elementaria and Psychologia
Peter Mulenga
Unknown Affiliation
Education Other

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

Found 1 Documents
Search

 1 
A COMPUTATIONAL MODEL OF LANGUAGE ACQUISITION: INTEGRATING NEURAL NETWORKS AND STATISTICAL LEARNING TO SIMULATE EARLY COGNITIVE DEVELOPMENT Isaac Chanda; Patricia Mumba; Peter Mulenga
International Journal of Educatio Elementaria and Psychologia Vol. 3 No. 2 (2026)
Publisher : Yayasan Adra Karima Hubbi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70177/ijeep.v3i2.3105

Abstract

Language acquisition in early childhood remains a complex process that integrates various cognitive mechanisms. Recent advancements in computational modeling have provided a new avenue for understanding how children learn language by simulating neural networks and statistical learning processes. This study presents a computational model that combines these two frameworks to simulate early cognitive development in the context of language acquisition. The aim of this research is to explore how neural networks, with their ability to process information through interconnected nodes, can mimic the way children acquire language. Additionally, the study integrates statistical learning, which is the process of extracting patterns from input data, to examine how it contributes to the learning of syntax and semantics in early language development. A combination of artificial neural networks (ANNs) and statistical learning algorithms was implemented to simulate language acquisition in a controlled environment. The results demonstrated that the model was able to replicate key features of language learning, such as word segmentation, syntax acquisition, and semantic understanding, with performance improving as the model was exposed to more data. The findings support the utility of computational models in studying cognitive processes and provide insights into how neural networks and statistical learning can work together to simulate language acquisition. The model’s applications could further enhance the understanding of language learning and the development of artificial intelligence.
Co-Authors Isaac Chanda Patricia Mumba