Harnessing the flexibility of neural networks to predict dynamic theoretical parameters underlying human choice behavior
PLOS Computational Biology · 04.01.2024 · 20 (1) · e1011678
DOI: 10.1371/journal.pcbi.1011678 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 04.01.2024. Verfasst von Yoav Ger und 3 weiteren Autor:innen. Beteiligte Einrichtung: Sagol School of Neuroscience, Tel-Aviv University, Tel-Aviv, Israel. Hauptthemen laut MEDLINE: Neural Networks, Computer, Reinforcement, Psychology. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Israeli Science Foundation, Tel Aviv University Center for AI and Data Science, Israel Precision Medicine Partnership program.
Abstract (Originalsprache)
Reinforcement learning (RL) models are used extensively to study human behavior. These rely on normative models of behavior and stress interpretability over predictive capabilities. More recently, neural network models have emerged as a descriptive modeling paradigm that is capable of high predictive power yet with limited interpretability. Here, we seek to augment the expressiveness of theoretical RL models with the high flexibility and predictive power of neural networks. We introduce a novel framework, which we term theoretical-RNN (t-RNN), whereby a recurrent neural network is trained to predict trial-by-trial behavior and to infer theoretical RL parameters using artificial data of RL agents performing a two-armed bandit task. In three studies, we then examined the use of our approach to dynamically predict unseen behavior along with time-varying theoretical RL parameters. We first validate our approach using synthetic data with known RL parameters. Next, as a proof-of-concept, we applied our framework to two independent datasets of humans performing the same task. In the first dataset, we describe differences in theoretical RL parameters dynamic among clinical psychiatric vs. healthy controls. In the second dataset, we show that the exploration strategies of humans varied dynamically in response to task phase and difficulty. For all analyses, we found better performance in the prediction of actions for t-RNN compared to the stationary maximum-likelihood RL method. We discuss the use of neural networks to facilitate the estimation of latent RL parameters underlying choice behavior.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Sagol School of Neuroscience, Tel-Aviv University, Tel-Aviv, Israel.
- School of Electrical Engineering, Tel-Aviv University, Tel-Aviv, Israel.
- Meta AI Research, Tel-Aviv, Israel.
- Blavatnik School of Computer Science, Tel-Aviv University, Tel-Aviv, Israel.
- School of Psychological Sciences, Tel-Aviv University, Tel-Aviv, Israel.
ORCID-Profile: Yoav Ger, Nitzan Shahar
Förderung
- Israeli Science Foundation
- Tel Aviv University Center for AI and Data Science
- Israel Precision Medicine Partnership program
- Israel Science Foundation
- the Israeli Science Foundation
Zitieren
APA
Ger, Y., Nachmani, E., Wolf, L., & Shahar, N. (2024). Harnessing the flexibility of neural networks to predict dynamic theoretical parameters underlying human choice behavior. PLOS Computational Biology, 20(1), e1011678. https://doi.org/10.1371/journal.pcbi.1011678
Vancouver
Ger Y, Nachmani E, Wolf L, Shahar N. Harnessing the flexibility of neural networks to predict dynamic theoretical parameters underlying human choice behavior. PLOS Computational Biology. 2024;20(1):e1011678. doi:10.1371/journal.pcbi.1011678
BibTeX
@article{Ger2024,
author = {Ger, Yoav and Nachmani, Eliya and Wolf, Lior and Shahar, Nitzan},
title = {Harnessing the flexibility of neural networks to predict dynamic theoretical parameters underlying human choice behavior},
journal = {PLOS Computational Biology},
year = {2024},
volume = {20},
number = {1},
pages = {e1011678},
doi = {10.1371/journal.pcbi.1011678}
}
EUVIMED