# Biological connectomes as a representation for the architecture of artificial neural networks

arXiv: https://arxiv.org/abs/2209.14406 · HTML: https://mlsanity.com/paper/2209.14406/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 60 references that are in the map.
- First posted on arXiv 28 Sep 2022.

## Builds on (most cited first, 12 of 12)

- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [A Critical Review of Recurrent Neural Networks for Sequence Learning](https://mlsanity.com/paper/1506.00019/) (2015)
- [Activation Functions: Comparison of trends in Practice and Research for Deep Learning](https://mlsanity.com/paper/1811.03378/) (2018)
- [Sparse DNNs with Improved Adversarial Robustness](https://mlsanity.com/paper/1810.09619/) (2018)
- [Meta-Learning through Hebbian Plasticity in Random Networks](https://mlsanity.com/paper/2007.02686/) (2020)
- [Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity](https://mlsanity.com/paper/2002.10585/) (2020)
- [SpikePropamine: Differentiable Plasticity in Spiking Neural Networks](https://mlsanity.com/paper/2106.02681/) (2021)
- [Neural Circuit Architectural Priors for Embodied Control](https://mlsanity.com/paper/2201.05242/) (2022)
- [Stable Lifelong Learning: Spiking neurons as a solution to instability in plastic neural networks](https://mlsanity.com/paper/2111.04113/) (2021)
- [Learning to learn online with neuromodulated synaptic plasticity in spiking neural networks](https://mlsanity.com/paper/2206.12520/) (2022)

## Built on by (most cited first, 2 of 2)

- [How Much is Brain Data Worth for Machine Learning?](https://mlsanity.com/paper/2605.09243/) (2026)
- [From the Drosophila Visual Connectome to General-Purpose Computer Vision](https://mlsanity.com/paper/2610.08418/) (2026)

## Abstract (arXiv)

Grand efforts in neuroscience are working toward mapping the connectomes of many new species, including the near completion of the Drosophila melanogaster. It is important to ask whether these models could benefit artificial intelligence. In this work we ask two fundamental questions: (1) where and when biological connectomes can provide use in machine learning, (2) which design principles are necessary for extracting a good representation of the connectome. Toward this end, we translate the motor circuit of the C. Elegans nematode into artificial neural networks at varying levels of biophysical realism and evaluate the outcome of training these networks on motor and non-motor behavioral tasks. We demonstrate that biophysical realism need not be upheld to attain the advantages of using biological circuits. We also establish that, even if the exact wiring diagram is not retained, the architectural statistics provide a valuable prior. Finally, we show that while the C. Elegans locomotion circuit provides a powerful inductive bias on locomotion problems, its structure may hinder performance on tasks unrelated to locomotion such as visual classification problems.