# A Drosophila Whole-Connectome Network Can Learn Human-Designed Cognitive Tasks

arXiv: https://arxiv.org/abs/2610.10014 · HTML: https://mlsanity.com/paper/2610.10014/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 3 of its 23 references that are in the map.
- First posted on arXiv 7 Oct 2026.

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

- [Whole-Brain Connectomic Graph Model Enables Whole-Body Locomotion Control in Fruit Fly](https://mlsanity.com/paper/2602.17997/) (2026)
- [Topological Sensitivity in Connectome-Constrained Neural Networks](https://mlsanity.com/paper/2604.04033/) (2026)
- [FLYNN: Robust Neural Network for Robot Navigation using Fly Brain Topology](https://mlsanity.com/paper/2607.00025/) (2026)

## Abstract (arXiv)

Can a biological wiring diagram serve as a useful computational substrate beyond the behaviors for which it evolved? We use the publicly released MaleCNS v1.0 connectome, reconstructed from a single adult male Drosophila specimen, as the fixed recurrent topology of an artificial network. We train separate models for bounded addition and for a controlled grounded relational language task built from a fixed 100-word lexicon. In both models, one scalar is learned per anatomical edge. The anatomical graph reaches 92.77% mean accuracy on held-out addition, compared with 67.93% for directed degree-preserving rewires. On the strict paired language endpoint, which matches original and order-reversed scenes to their corresponding descriptions, it reaches 61.59% across four fixed interfaces, compared with 44.17% for matched rewires. At the canonical interface, it ranks first in a fixed 21-graph comparison. On the matched 48-group intervention subset, shuffling task-defined sensory features reduces its score from 60.94% to 19.27%. Together, these results show that higher-order MaleCNS wiring provides a reusable inductive bias for bounded addition and grounded relational language.