# How Biological Synapses Self-Assemble Gradient Learning

arXiv: https://arxiv.org/abs/2412.20018 · HTML: https://mlsanity.com/paper/2412.20018/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2024.

## Built on by (most cited first, 5 of 5)

- [Hierarchical Reasoning Models: Perspectives and Misconceptions](https://mlsanity.com/paper/2510.00355/) (2025)
- [Ubiquity of Emergent Hebbian Dynamics in Regularized Learning](https://mlsanity.com/paper/2505.18069/) (2025)
- [Does Feedback Alignment Work at Biological Timescales?](https://mlsanity.com/paper/2510.18808/) (2025)
- [Modular connectivity in neural networks emerges from Poisson noise-motivated regularisation, and promotes robustness and compositional generalisation](https://mlsanity.com/paper/2512.13707/) (2025)
- [Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks](https://mlsanity.com/paper/2606.14975/) (2026)

## Abstract (arXiv)

Existing models of learning in the brain explain how given circuits learn, but not how biology could assemble those circuits in the first place. To address this gap, we formulate Self-Assembling Learning (SAL)---the study of how learning systems can emerge from lower-level interactions---and introduce one example mechanism, the Self-Assembling Motif (SAM). SAM is self-assembling at two scales: the motif emerges from initially random connectivity under heterosynaptic plasticity rules, and networks of SAMs, composed hierarchically, self-organize into dynamics that provably approximate a generalized form of stochastic gradient descent---matching backpropagation-level performance. This suggests that biological learning need not be prescribed but can emerge from local rules---and to a far greater extent than previously thought.