# Modeling the dynamics of human brain activity with recurrent neural networks

arXiv: https://arxiv.org/abs/1606.03071 · HTML: https://mlsanity.com/paper/1606.03071/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2016.

## Built on by (most cited first, 12 of 12)

- [TRIBE: TRImodal Brain Encoder for whole-brain fMRI response prediction](https://mlsanity.com/paper/2507.22229/) (2025)
- [A foundation model of vision, audition, and language for in-silico neuroscience](https://mlsanity.com/paper/2605.04326/) (2026)
- [Deep Recurrent Encoder: A scalable end-to-end network to model brain signals](https://mlsanity.com/paper/2103.02339/) (2021)
- [Neural Co-Processors for Restoring Brain Function: Results from a Cortical Model of Grasping](https://mlsanity.com/paper/2210.11478/) (2022)
- [Continuous Homeostatic Reinforcement Learning for Self-Regulated Autonomous Agents](https://mlsanity.com/paper/2109.06580/) (2021)
- [Symmetry Perception by Deep Networks: Inadequacy of Feed-Forward Architectures and Improvements with Recurrent Connections](https://mlsanity.com/paper/2112.04162/) (2021)
- [Estimating Reproducible Functional Networks Associated with Task Dynamics using Unsupervised LSTMs](https://mlsanity.com/paper/2105.02869/) (2021)
- [Modelling Neuronal Behaviour with Time Series Regression: Recurrent Neural Networks on C. Elegans Data](https://mlsanity.com/paper/2107.06762/) (2021)
- [Improving the Level of Autism Discrimination through GraphRNN Link Prediction](https://mlsanity.com/paper/2202.09538/) (2022)
- [SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks](https://mlsanity.com/paper/2206.08427/) (2022)
- [Paradoxical noise preference in RNNs](https://mlsanity.com/paper/2601.04539/) (2026)
- [Probabilistic Prediction of Neural Dynamics via Autoregressive Flow Matching](https://mlsanity.com/paper/2604.11178/) (2026)

## Abstract (arXiv)

Encoding models are used for predicting brain activity in response to sensory stimuli with the objective of elucidating how sensory information is represented in the brain. Encoding models typically comprise a nonlinear transformation of stimuli to features (feature model) and a linear transformation of features to responses (response model). While there has been extensive work on developing better feature models, the work on developing better response models has been rather limited. Here, we investigate the extent to which recurrent neural network models can use their internal memories for nonlinear processing of arbitrary feature sequences to predict feature-evoked response sequences as measured by functional magnetic resonance imaging. We show that the proposed recurrent neural network models can significantly outperform established response models by accurately estimating long-term dependencies that drive hemodynamic responses. The results open a new window into modeling the dynamics of brain activity in response to sensory stimuli.