High-rank connectivity scaffolds support precision and generalisation in recurrent neural networks
Year: 2026
Type: preprint
Abstract: A major challenge in neuroscience and machine learning is to connect single-neuron influence, population dynamics, and circuit connectivity in a causal account of computation. Much previous work has shown that low-rank connectivity can generate low-dimensional dynamics in trained artificial neural networks, but this leaves unclear the functional relevance of the higher-rank structure of biological neural circuits and many artificial neuronal networks. Here we analyse recurrent neural networks trained to locate rewards by integrating continuously varying speed inputs in one- and two-dimensional spatial tasks. We find that dominant low-dimensional dynamics encode task locations, and can be causally manipulated to instruct behavioural outcomes. However, after decomposing the underlying circuitry we found that while low-rank connectivity accounts for the low-dimensional dynamics, accurate performance and generalisation to novel speed distributions requires high-rank connectivity. We demonstrate that this is achieved through distributed signalling that corrects errors in low-dimensional location representations. Thus, combined perturbation-, representation-, and circuit-level analyses demonstrate a novel mechanism for robust spatial computation and show how high-rank connectivity in neural circuits can provide a scaffold that supports precision and generalisation.
Source: arXiv (Cornell University)
Authors: Hawes, Ian, Nolan, Matt
Institution: University of Edinburgh
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: green
Awards: Intra- and inter-layer entorhinal circuit mechanisms for estimating location, Enhancing automated, reproducible analysis workflows and data curation for extracellular neural recordings with SpikeInterface, Intra- and inter-layer entorhinal circuit mechanisms for estimating location, Translational Neuroscience - training the next generation of basic neuroscientists to embrace clinical research., G6212508579, G9000063527
OpenAlex ID: W7214793954