# Autonomous Learning of Generative Models with Chemical Reaction Network Ensembles

arXiv: https://arxiv.org/abs/2311.00975 · HTML: https://mlsanity.com/paper/2311.00975/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 62 references that are in the map.
- First posted on arXiv 2 Nov 2023.

## Builds on (most cited first, 3 of 3)

- [Why does deep and cheap learning work so well?](https://mlsanity.com/paper/1608.08225/) (2016)
- [On reaction network implementations of neural networks](https://mlsanity.com/paper/2010.13290/) (2020)
- [Detailed Balanced Chemical Reaction Networks as Generalized Boltzmann Machines](https://mlsanity.com/paper/2205.06313/) (2022)

## Built on by (most cited first, 3 of 3)

- [Implementation of reinforcement learning in chemical reaction networks: application to phototaxis as curiosity-driven exploration](https://mlsanity.com/paper/2606.26168/) (2026)
- [Neural CRNs: A Natural Implementation of Learning in Chemical Reaction Networks](https://mlsanity.com/paper/2409.00034/) (2024)
- [An all-transistor physical-learning transformer can be trained to perform in-context learning](https://mlsanity.com/paper/2610.12571/) (2026)

## Abstract (arXiv)

Can a micron sized sack of interacting molecules autonomously learn an internal model of a complex and fluctuating environment? We draw insights from control theory, machine learning theory, chemical reaction network theory, and statistical physics to develop a general architecture whereby a broad class of chemical systems can autonomously learn complex distributions. Our construction takes the form of a chemical implementation of machine learning's optimization workhorse: gradient descent on the relative entropy cost function. We show how this method can be applied to optimize any detailed balanced chemical reaction network and that the construction is capable of using hidden units to learn complex distributions. This result is then recast as a form of integral feedback control. Finally, due to our use of an explicit physical model of learning, we are able to derive thermodynamic costs and trade-offs associated to this process.