Artificial Neural Networks and the Actiotope Model of Giftedness-Clever Solutions from Complex Environments

• Published in: Journal of intelligence Vol. 11; no. 7; p. 128
• Main Authors: Phillipson, Shane N, Han, Cindy Di, Lee, Vincent C S
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 25-06-2023; MDPI
• Subjects: Academic achievement; Actiotope Model of Giftedness; artificial neural networks; Baker, Joseph; complexity; Concept Paper; Gifted education; Learning; Learning strategies; Mathematics; Neural networks; Regulation; Students; Teachers; Saudi Arabia; Australia; Germany; artificial neural networks; complexity; Actiotope Model of Giftedness; research
• ISSN: 2079-3200; 2079-3200
• DOI: 10.3390/jintelligence11070128

Since its inception, the Actiotope Model of Giftedness (AMG) has provided researchers with a useful model to explain the development of exceptionality. Rather than a focus on the individual, the model postulates that exceptionality is the outcome of a system that includes complex interactions between an individual's current level of talent and their internal and external environment. To date, however, the statistical techniques that have been used to investigate the model, including linear regression and structural equation modeling, are unable to fully operationalize the systemic nature of these interactions. In order to fully realize the predictive potential and application of the AMG, we outline the use of artificial neural networks (ANNs) to model the complex interactions and suggest that such networks can provide additional insights into the development of exceptionality. In addition to supporting continued research into the AMG, the use of ANNs has the potential to provide educators with evidence-based strategies to support student learning at both an individual and whole-school level.