# Input-driven circuit reconfiguration in critical recurrent neural networks

arXiv: https://arxiv.org/abs/2405.15036 · HTML: https://mlsanity.com/paper/2405.15036/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 50 references that are in the map.
- First posted on arXiv 23 May 2024.

## Builds on (most cited first, 8 of 8)

- [Unitary Evolution Recurrent Neural Networks](https://mlsanity.com/paper/1511.06464/) (2015)
- [projUNN: efficient method for training deep networks with unitary matrices](https://mlsanity.com/paper/2203.05483/) (2022)
- [Interpreting neural computations by examining intrinsic and embedding dimensionality of neural activity](https://mlsanity.com/paper/2107.04084/) (2021)
- [Traveling Waves Encode the Recent Past and Enhance Sequence Learning](https://mlsanity.com/paper/2309.08045/) (2023)
- [Complex Unitary Recurrent Neural Networks using Scaled Cayley Transform](https://mlsanity.com/paper/1811.04142/) (2018)
- [Hidden Traveling Waves bind Working Memory Variables in Recurrent Neural Networks](https://mlsanity.com/paper/2402.10163/) (2024)
- [Convolutional unitary or orthogonal recurrent neural networks](https://mlsanity.com/paper/2302.07396/) (2023)
- [On the dynamics of convolutional recurrent neural networks near their critical point](https://mlsanity.com/paper/2405.13854/) (2024)

## Abstract (arXiv)

Changing a circuit dynamically, without actually changing the hardware itself, is called reconfiguration, and is of great importance due to its manifold technological applications. Circuit reconfiguration appears to be a feature of the cerebral cortex, and hence understanding the neuroarchitectural and dynamical features underlying self-reconfiguration may prove key to elucidate brain function. We present a very simple single-layer recurrent network, whose signal pathways can be reconfigured "on the fly" using only its inputs, with no changes to its synaptic weights. We use the low spatio-temporal frequencies of the input to landscape the ongoing activity, which in turn permits or denies the propagation of traveling waves. This mechanism uses the inherent properties of dynamically-critical systems, which we guarantee through unitary convolution kernels. We show this network solves the classical connectedness problem, by allowing signal propagation only along the regions to be evaluated for connectedness and forbidding it elsewhere.