# The Drosophila Connectome as a Computational Reservoir for Time-Series Prediction

## TL;DR

Researchers used the fruit fly's brain connections to predict chaotic time-series data, finding it more resilient to overfitting than standard methods.

## Contribution

The study introduces a novel use of the Drosophila connectome as a reservoir for time-series prediction, demonstrating improved overfitting resilience.

## Key findings

- Connectome-based reservoirs show greater resilience to overfitting compared to standard implementations.
- Hybrid reservoirs reveal that both topology and synaptic weights contribute to overfitting resilience.
- Using the full connectome as a reservoir results in lower normalized error with less regularization.

## Abstract

In this work, we explore the possibility of using the topology and weight distribution of the connectome of a Drosophila, or fruit fly, as a reservoir for multivariate chaotic time-series prediction. Based on the information taken from the recently released full connectome, we create the connectivity matrix of an Echo State Network. Then, we use only the most connected neurons and implement two possible selection criteria, either preserving or breaking the relative proportion of different neuron classes which are also included in the documented connectome, to obtain a computationally convenient reservoir. We then investigate the performance of such architectures and compare them to state-of-the-art reservoirs. The results show that the connectome-based architecture is significantly more resilient to overfitting compared to the standard implementation, particularly in cases already prone to overfitting. To further isolate the role of topology and synaptic weights, hybrid reservoirs with the connectome topology but random synaptic weights and the connectome weights but random topologies are included in the study, demonstrating that both factors play a role in the increased overfitting resilience. Finally, we perform an experiment where the entire connectome is used as a reservoir. Despite the much higher number of trained parameters, the reservoir remains resilient to overfitting and has a lower normalized error, under 2%, at lower regularisation, compared to all other reservoirs trained with higher regularisation.