Can a Fruit Fly Brain Learn Numbers?

A 499-neuron circuit extracted from MaleCNS v1.0, the Janelia-published CC-BY electron-microscopy reconstruction of a male fruit fly's central nervous system, was run as a reservoir on MNIST in PyTorch and MLX, matching the 499-neuron count reported in the underlying paper but yielding 13,452 directed edges against the paper's reported 15,865. The reproduction applied the original selection rule — central-brain intrinsic neurons, traced status, ranked by strength, top 512, largest strongly connected component, edges with at least 5 synaptic contacts — and the author noted the paper's exact ranking formula for "strongest" is unpublished, making this the closest match achievable. Code and data were released via a public gist.

Following up on A Fruit Fly Circuit as a Speech Emotion Reservoir https://julin.ai/2026/09/09/fly-brain-emotion/ : I pulled the real 499-neuron circuit out of MaleCNS v1.0 and ran it as a reservoir on MNIST, in PyTorch and in MLX https://github.com/ml-explore/mlx . Code and data: gist https://gist.github.com/soasme/caa8b071e85d76aff44aec8f259d0870 . MaleCNS v1.0 https://male-cns.janelia.org/download/ is a public, CC-BY electron-microscopy reconstruction of a male fruit fly’s central nervous system. I applied the selection rule stated in the original article: central-brain intrinsic neurons, traced status, ranked by strength, top 512, largest strongly connected component, edges with at least 5 synaptic contacts. This landed on exactly 499 neurons — the same count the paper reports — with 13,452 directed edges, against their reported 15,865. Their exact ranking formula for “strongest” isn’t published, so this is the closest match I could reproduce.