Mapping differential responses to cognitive training using machine learning
| Autor: | Duncan E. Astle, Erin Hawkins, Mengya Zhang, Joe Bathelt, Joseph P Rennie |
|---|---|
| Přispěvatelé: | Brein en Cognitie (Psychologie, FMG), Bathelt, Joe [0000-0001-5195-956X], Apollo - University of Cambridge Repository |
| Rok vydání: | 2018 |
| Předmět: |
Male
Special Issue Articles Adolescent Cognitive Neuroscience Intelligence Short-term memory Machine learning computer.software_genre 050105 experimental psychology individual difference cognitive training Cognition Developmental and Educational Psychology Cognitive development Cluster Analysis Humans 0501 psychology and cognitive sciences Cluster analysis Child development Intelligence quotient Working memory business.industry 05 social sciences Special Issue Article Cognitive training Memory Short-Term machine learning Child Preschool Task analysis Unsupervised learning Female Artificial intelligence Psychology business Cognition Disorders computer 050104 developmental & child psychology Unsupervised Machine Learning |
| Zdroj: | Developmental Science Developmental Science, 23(4):e12868. Wiley-Blackwell |
| ISSN: | 1467-7687 1363-755X |
| Popis: | We used two simple unsupervised machine learning techniques to identify differential trajectories of change in children who undergo intensive working memory (WM) training. We used self‐organizing maps (SOMs)—a type of simple artificial neural network—to represent multivariate cognitive training data, and then tested whether the way tasks are represented changed as a result of training. The patterns of change we observed in the SOM weight matrices implied that the processes drawn upon to perform WM tasks changed following training. This was then combined with K‐means clustering to identify distinct groups of children who respond to the training in different ways. Firstly, the K‐means clustering was applied to an independent large sample (N = 616, M age = 9.16 years, range = 5.16–17.91 years) to identify subgroups. We then allocated children who had been through cognitive training (N = 179, M age = 9.00 years, range = 7.08–11.50 years) to these same four subgroups, both before and after their training. In doing so, we were able to map their improvement trajectories. Scores on a separate measure of fluid intelligence were predictive of a child's improvement trajectory. This paper provides an alternative approach to analysing cognitive training data that go beyond considering changes in individual tasks. This proof‐of‐principle demonstrates a potentially powerful way of distinguishing task‐specific from domain‐general changes following training and of establishing different profiles of response to training. (a) Pre‐ and post‐ working memory (WM) training datasets from 179 children were used to train self‐organizing maps (SOM), a unsupervised machine learning algorithm that represents multivariate task relationships in a 2‐dimentional space, (b) WM task relationships as represented by SOM changed as a result of training, indicating that the processes drawn upon to perform these tasks were altered. Improvements might be due to task‐specific rather than domaingeneral enhancement and (c) There were differential improvement profiles among children and and independent measure of fluid intelligence at pre‐training is predictive of these profiles. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text