NeuralRNN: a unified framework for recurrent neural network methods in cognitive neuroscience
- 1Zhejiang University
Abstract
Recurrent neural networks (RNNs) provide a central tool in neuroscience to optimize cognitive tasks and reconstruct dynamical systems. Around these two paradigms, many RNN model variants have been tailored to capture specific computations of the brain. In practice, however, this methodological diversity remains difficult to exploit, because different paradigms and model variants are mostly implemented in idiosyncratic, study-specific code. Here we introduce NeuralRNN, an open-source Python framework that unifies these paradigms and model variants in a general-purpose pipeline. NeuralRNN brings task optimization, dynamical system reconstruction, and biological constraints into a single objective interface. It also provides an integrated and extensible model library spanning generic, structure-constrained, gain-modulated, and gated RNNs. Furthermore, data, models, and training are constructed through a shared automated pipeline and are equipped with a suite of tools for dynamical systems analysis. Together, NeuralRNN lowers the barrier to implementing, comparing, and extending RNN methods in neuroscience.
Related
- Neurocognition of dance: Guidelines for using dance as model behavior and research subject in cognitive neuroscience
- Ten simple rules for achieving computational reproducibility in cognitive neuroscience
- Neuro-XR Primer: Blending Neuroscience and Extended Reality to Facilitate Cognitive Investigation.
- Cognitive Warfare Through the Lens of Critical Neuroscience: Data, Theory, and Values
- Take it personally: Promoting a personalised neuroscience informed approach to cognitive rehabilitation following psychopathology.
BibTeX
@misc{chen2026neuralrnn,
title = {{NeuralRNN: a unified framework for recurrent neural network methods in cognitive neuroscience}},
author = {H. Chen and N. Ding},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.14.751453},
url = {https://www.biorxiv.org/content/10.64898/2026.09.14.751453v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - NeuralRNN: a unified framework for recurrent neural network methods in cognitive neuroscience
AU - H. Chen
AU - N. Ding
PY - 2026
DA - 2026/09/14
PB - bioRxiv
DO - 10.64898/2026.09.14.751453
UR - https://www.biorxiv.org/content/10.64898/2026.09.14.751453v1
AB - Recurrent neural networks (RNNs) provide a central tool in neuroscience to optimize cognitive tasks and reconstruct dynamical systems. Around these two paradigms, many RNN model variants have been tailored to capture specific computations of the brain. In practice, however, this methodological diversity remains difficult to exploit, because different paradigms and model variants are mostly implemented in idiosyncratic, study-specific code. Here we introduce NeuralRNN, an open-source Python framework that unifies these paradigms and model variants in a general-purpose pipeline. NeuralRNN brings task optimization, dynamical system reconstruction, and biological constraints into a single objective interface. It also provides an integrated and extensible model library spanning generic, structure-constrained, gain-modulated, and gated RNNs. Furthermore, data, models, and training are constructed through a shared automated pipeline and are equipped with a suite of tools for dynamical systems analysis. Together, NeuralRNN lowers the barrier to implementing, comparing, and extending RNN methods in neuroscience.
ER -