# Learning without gradient descent encoded by the dynamics of a neurobiological model

arXiv: https://arxiv.org/abs/2103.08878 · HTML: https://mlsanity.com/paper/2103.08878/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 16 Mar 2021.

## Builds on (most cited first, 7 of 7)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [The Effect of Signaling Latencies and Node Refractory States on the Dynamics of Networks](https://mlsanity.com/paper/1804.07609/) (2018)
- [Construction of edge-ordered multidirected graphlets for comparing dynamics of spatial temporal neural networks](https://mlsanity.com/paper/2006.15971/) (2020)

## Abstract (arXiv)

The success of state-of-the-art machine learning is essentially all based on different variations of gradient descent algorithms that minimize some version of a cost or loss function. A fundamental limitation, however, is the need to train these systems in either supervised or unsupervised ways by exposing them to typically large numbers of training examples. Here, we introduce a fundamentally novel conceptual approach to machine learning that takes advantage of a neurobiologically derived model of dynamic signaling, constrained by the geometric structure of a network. We show that MNIST images can be uniquely encoded and classified by the dynamics of geometric networks with nearly state-of-the-art accuracy in an unsupervised way, and without the need for any training.