Deep latent variable joint cognitive modeling of neural signals and human behavior
As the field of computational cognitive neuroscience continues to expand and generate new theories, there is a growing need for more advanced methods to test the hypothesis of brain-behavior relationships. Recent progress in Bayesian cognitive modeling has enabled the combination of neural and behav...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-05-01
|
Series: | NeuroImage |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811924000545 |
_version_ | 1797215983142699008 |
---|---|
author | Khuong Vo Qinhua Jenny Sun Michael D. Nunez Joachim Vandekerckhove Ramesh Srinivasan |
author_facet | Khuong Vo Qinhua Jenny Sun Michael D. Nunez Joachim Vandekerckhove Ramesh Srinivasan |
author_sort | Khuong Vo |
collection | DOAJ |
description | As the field of computational cognitive neuroscience continues to expand and generate new theories, there is a growing need for more advanced methods to test the hypothesis of brain-behavior relationships. Recent progress in Bayesian cognitive modeling has enabled the combination of neural and behavioral models into a single unifying framework. However, these approaches require manual feature extraction, and lack the capability to discover previously unknown neural features in more complex data. Consequently, this would hinder the expressiveness of the models. To address these challenges, we propose a Neurocognitive Variational Autoencoder (NCVA) to conjoin high-dimensional EEG with a cognitive model in both generative and predictive modeling analyses. Importantly, our NCVA enables both the prediction of EEG signals given behavioral data and the estimation of cognitive model parameters from EEG signals. This novel approach can allow for a more comprehensive understanding of the triplet relationship between behavior, brain activity, and cognitive processes. |
first_indexed | 2024-04-24T11:38:44Z |
format | Article |
id | doaj.art-bf388d61bf844ca5a851c62a3c9a0227 |
institution | Directory Open Access Journal |
issn | 1095-9572 |
language | English |
last_indexed | 2024-04-24T11:38:44Z |
publishDate | 2024-05-01 |
publisher | Elsevier |
record_format | Article |
series | NeuroImage |
spelling | doaj.art-bf388d61bf844ca5a851c62a3c9a02272024-04-10T04:28:38ZengElsevierNeuroImage1095-95722024-05-01291120559Deep latent variable joint cognitive modeling of neural signals and human behaviorKhuong Vo0Qinhua Jenny Sun1Michael D. Nunez2Joachim Vandekerckhove3Ramesh Srinivasan4Department of Computer Science, University of California, Irvine, USA; Correspondence to: Department of Computer Science, University of California, Irvine, CA, 92697, USA.Department of Cognitive Sciences, University of California, Irvine, USAPsychological Methods, University of Amsterdam, The NetherlandsDepartment of Cognitive Sciences, University of California, Irvine, USA; Department of Statistics, University of California, Irvine, USADepartment of Cognitive Sciences, University of California, Irvine, USA; Department of Biomedical Engineering, University of California, Irvine, USAAs the field of computational cognitive neuroscience continues to expand and generate new theories, there is a growing need for more advanced methods to test the hypothesis of brain-behavior relationships. Recent progress in Bayesian cognitive modeling has enabled the combination of neural and behavioral models into a single unifying framework. However, these approaches require manual feature extraction, and lack the capability to discover previously unknown neural features in more complex data. Consequently, this would hinder the expressiveness of the models. To address these challenges, we propose a Neurocognitive Variational Autoencoder (NCVA) to conjoin high-dimensional EEG with a cognitive model in both generative and predictive modeling analyses. Importantly, our NCVA enables both the prediction of EEG signals given behavioral data and the estimation of cognitive model parameters from EEG signals. This novel approach can allow for a more comprehensive understanding of the triplet relationship between behavior, brain activity, and cognitive processes.http://www.sciencedirect.com/science/article/pii/S1053811924000545EEGDecision makingNeurocognitive modelDrift-diffusion modelVariational BayesDeep learning |
spellingShingle | Khuong Vo Qinhua Jenny Sun Michael D. Nunez Joachim Vandekerckhove Ramesh Srinivasan Deep latent variable joint cognitive modeling of neural signals and human behavior NeuroImage EEG Decision making Neurocognitive model Drift-diffusion model Variational Bayes Deep learning |
title | Deep latent variable joint cognitive modeling of neural signals and human behavior |
title_full | Deep latent variable joint cognitive modeling of neural signals and human behavior |
title_fullStr | Deep latent variable joint cognitive modeling of neural signals and human behavior |
title_full_unstemmed | Deep latent variable joint cognitive modeling of neural signals and human behavior |
title_short | Deep latent variable joint cognitive modeling of neural signals and human behavior |
title_sort | deep latent variable joint cognitive modeling of neural signals and human behavior |
topic | EEG Decision making Neurocognitive model Drift-diffusion model Variational Bayes Deep learning |
url | http://www.sciencedirect.com/science/article/pii/S1053811924000545 |
work_keys_str_mv | AT khuongvo deeplatentvariablejointcognitivemodelingofneuralsignalsandhumanbehavior AT qinhuajennysun deeplatentvariablejointcognitivemodelingofneuralsignalsandhumanbehavior AT michaeldnunez deeplatentvariablejointcognitivemodelingofneuralsignalsandhumanbehavior AT joachimvandekerckhove deeplatentvariablejointcognitivemodelingofneuralsignalsandhumanbehavior AT rameshsrinivasan deeplatentvariablejointcognitivemodelingofneuralsignalsandhumanbehavior |