![]() ![]() Adaptive and extended WM training often improves WM skill ( Soveri et al., 2017) however, the extent to which this type of training produces improvements that generalize far beyond the training task remains controversial ( Melby-Lervåg and Hulme, 2013 Melby-Lervåg et al., 2016). For example, one of the most popular approaches is to train working memory (WM), a limited-capacity system involved in temporary storage and manipulation of information ( Baddeley, 2012). Over the last decade, the scientific topic of improving cognitive capacity by leveraging the plasticity of the brain has gathered both significant interest and controversies regarding effectiveness ( Karbach and Unger, 2014 Au et al., 2016 Melby-Lervåg et al., 2016 Simons et al., 2016 Green et al., 2018 Soveri et al., 2018 Redick, 2019). These data provide good support for the potential of machine learning approaches as appropriate methods to personalize task performance to users in tasks that require adaptively determined challenges. ![]() However, the hidden Markov models were most accurate in predicting participants' performances as a function of provided challenges, and thus, they placed participants at appropriate future challenges. Results show that all three models predict appropriate challenges for different users. As a proof of concept, we fit data from two large cohorts of undergraduate students performing WM training using an N-back task. A possible advantage of these models over commonly used adaptive methods, such as staircases or blockwise adjustment methods that are based only upon recent performance, is that Bayesian filtering and deep learning approaches can model the trajectory of user performance across multiple sessions and incorporate data from multiple users to optimize local estimates. Here we examine how Bayesian filtering approaches, such as hidden Markov models and Kalman filters, and deep-learning approaches, such as the long short-term memory (LSTM) model, may be useful methods to estimate user skill level and predict appropriate task challenges. 4Department of Psychology, University of California, Riverside, Riverside, CA, United StatesĪ key need in cognitive training interventions is to personalize task difficulty to each user and to adapt this difficulty to continually apply appropriate challenges as users improve their skill to perform the tasks.3School of Education, University of California, Irvine, Irvine, CA, United States.2Brain Game Center, University of California, Riverside, Riverside, CA, United States.1Department of Computer Science, University of California, Riverside, Riverside, CA, United States.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |