10.1016/j.rinam.2026.100730">
 

Document Type

Article

Publication Date

6-19-2026

Abstract

In this paper, we use the Duolingo SLAM dataset to analyze several cognitive models of second language acquisition and develop new approaches for enhanced performance. In particular, we consider the Predictive Performance Equation and some of its underlying power laws. Leveraging insights from machine learning, we develop simple one-feature models as building blocks for combined models that match or in certain cases outperform the existing models at much reduced computational cost. In addition, a neural network with one fully connected hidden layer is constructed that outperforms all other models on sufficiently large datasets.

Comments

© 2026 The Authors.

This article is published by Elsevier, licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Sourced from the published version of record cited below.

Status note: This article was published online as a version of record by Elsevier in advance of inclusion in the August 2026 issue.

Funding note: Financial support was provided by Joint Hypersonics Transition Office (JHTO), managed by the Applied Research Center for Hypersonics (ARCH) at the Air Force Institute of Technology.

Source Publication

Results in Applied Mathematics (eISSN 2590-0374)

Share

COinS