# Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks

arXiv: https://arxiv.org/abs/2606.14975 · HTML: https://mlsanity.com/paper/2606.14975/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 79 references that are in the map.
- First posted on arXiv 12 Jun 2026.

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

- [Towards an integration of deep learning and neuroscience](https://mlsanity.com/paper/1606.03813/) (2016)
- [The physics of brain network structure, function, and control](https://mlsanity.com/paper/1809.06441/) (2018)
- [The interplay between randomness and structure during learning in RNNs](https://mlsanity.com/paper/2006.11036/) (2020)
- [Winning the lottery with neural connectivity constraints: faster learning across cognitive tasks with spatially constrained sparse RNNs](https://mlsanity.com/paper/2207.03523/) (2022)
- [How Biological Synapses Self-Assemble Gradient Learning](https://mlsanity.com/paper/2412.20018/) (2024)
- [Spatial embedding promotes a specific form of modularity with low entropy and heterogeneous spectral dynamics](https://mlsanity.com/paper/2409.17693/) (2024)
- [Exploiting Large Neuroimaging Datasets to Create Connectome-Constrained Approaches for more Robust, Efficient, and Adaptable Artificial Intelligence](https://mlsanity.com/paper/2305.17300/) (2023)
- [Global and local synchrony of coupled neurons in small-world networks](https://mlsanity.com/paper/2411.16374/) (2024)

## Abstract (arXiv)

How the wiring and functional organization of cortex shape recurrent computation remains a central question in both neuroscience and machine learning. Here, we leverage data released through the Machine Intelligence from Cortical Networks (MICrONS) program--a functional connectomics resource spanning multiple areas of mouse visual cortex, in which dense calcium imaging is co-registered with high-resolution electron microscopy reconstruction from the same animal--to build biologically grounded recurrent neural networks. Using neuronal spatial coordinates, anatomical connectivity, and function-derived relationships from nearly 12,000 coregistered excitatory neurons, we initialize recurrent weights and impose communication-aware spatial constraints during learning. Across three cognitive decision-making tasks, networks constrained by cortical structure and function consistently outperform baseline and partially constrained models. Functional weight initialization provides the largest gain, while real spatial embedding yields robust additional improvements across conditions. These biologically grounded networks also develop low-entropy, modular, and small-world organization, and retain strong performance even when recurrence is restricted to positive weights. Together, our results show that the machinery of cortex--its geometry, wiring, and functional structure--can be harnessed as a powerful inductive basis for building recurrent networks that learn more effectively while converging toward key organizational principles of biological computation.