# Association-sensory spatiotemporal hierarchy and functional gradient-regularised recurrent neural network with implications for schizophrenia

arXiv: https://arxiv.org/abs/2511.02722 · HTML: https://mlsanity.com/paper/2511.02722/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 104 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 5 of 5)

- [Optimal modularity and memory capacity of neural reservoirs](https://mlsanity.com/paper/1706.06511/) (2017)
- [Emergence and reconfiguration of modular structure for synaptic neural networks during continual familiarity detection](https://mlsanity.com/paper/2311.05862/) (2023)
- [Learning-Induced Autonomy of Sensorimotor Systems](https://mlsanity.com/paper/1403.6034/) (2014)
- [A mechanistic model of connector hubs, modularity, and cognition](https://mlsanity.com/paper/1803.08109/) (2018)
- [Choosing Wavelet Methods, Filters, and Lengths for Functional Brain Network Construction](https://mlsanity.com/paper/1512.07596/) (2015)

## Abstract (arXiv)

The human neocortex is functionally organised at its highest level along a continuous sensory-to-association (AS) hierarchy. This study characterises the AS hierarchy of patients with schizophrenia in a comparison with controls. Using a large fMRI dataset (N=355), we extracted individual AS gradients via spectral analysis of brain connectivity, quantified hierarchical specialisation by gradient spread, and related this spread with connectivity geometry. We found that schizophrenia compresses the AS hierarchy indicating reduced functional differentiation. By modelling neural timescale with the Ornstein-Uhlenbeck process, we observed that the most specialised, locally cohesive regions at the gradient extremes exhibit dynamics with a longer time constant, an effect that is attenuated in schizophrenia. To study computation, we used the gradients to regularise subject-specific recurrent neural networks (RNNs) trained on working memory tasks. Networks endowed with greater gradient spread learned more efficiently, plateaued at lower task loss, and maintained stronger alignment to the prescribed AS hierarchical geometry. Fixed point linearisation showed that high-range networks settled into more stable neural states during memory delay, evidenced by lower energy and smaller maximal Jacobian eigenvalues. This gradient-regularised RNN framework therefore links large-scale cortical architecture with fixed point stability, providing a mechanistic account of how gradient de-differentiation could destabilise neural computations in schizophrenia, convergently supported by empirical timescale flattening and model-based evidence of less stable fixed points.