Dodam Ih | The Path to the Mouse Connectome @ Vision Weekend Puerto Rico 2026

Why It Matters

A complete mouse connectome validates the AI‑centric workflow needed to tackle the human brain, unlocking new avenues in neuroscience, precision medicine and next‑generation artificial intelligence.

Key Takeaways

• Zeta AI aims to map mouse brain by 2034.
• New pipeline handles severe imaging defects via AI alignment.
• Proofreading model cuts merge errors by 51% using geometry.
• Human‑AI loop accelerates segmentation across 11 species globally.
• Success on mouse brain will enable human brain connectomics.

Summary

At Vision Weekend Puerto Rico 2026, Totem E, founding engineer at Zeta AI, outlined the company’s roadmap to produce a complete wiring diagram of the mouse brain—a stepping stone toward the ultimate goal of mapping the 86 billion‑neuron human brain.

Zeta’s end‑to‑end pipeline converts thousands of electron‑microscope sections into a 3‑D connectome by assembling volumes, segmenting individual neurons, detecting synapses and then proof‑reading. By tackling the notoriously noisy serial‑section TEM data, the team trained neural nets to align across up to five missing sections and even generate plausible tissue to bridge gaps. Leveraging lessons from the Flywire project, they anticipate full mouse‑brain segmentation by 2032 and human‑level proof‑reading by 2034, representing a 6,500‑fold scale‑up.

A key breakthrough is a geometry‑focused proofreading model that, after training on just 0.5 % of the data, eliminated 51 % of merge errors while preserving completeness—validated on a dataset six times larger. The same pipeline now handles data from 11 species across modalities, from X‑ray tomography to light‑expansion microscopy, illustrating the robustness of the human‑AI feedback loop.

If successful, the mouse connectome will provide the first mammalian cortical map, accelerating drug discovery, disease modeling and AI safety research, and proving that AI‑driven proof‑reading can eventually scale to the human brain’s 86 billion neurons. Zeta’s invitation for collaborators underscores the race to turn this proof‑of‑concept into a universal brain‑mapping platform.

Original Description

This talk is part of Vision Weekend Puerto Rico 2026, a three-day gathering of researchers and builders in Old San Juan.

The program featured 30+ presentations, along with keynotes, lightning talks, office hours, and discussions focused on “AI for X” — exploring how AI is advancing fields like neurotech, biotech, energy, and beyond.

https://foresight.org/events/vision-weekend-puerto-rico-2026/

══════════════════════════════════════

About The Foresight Institute

The Foresight Institute is a research organization and non-profit that supports the beneficial development of high-impact technologies. Since our founding in 1986 on a vision of guiding powerful technologies, we have continued to evolve into a many-armed organization that focuses on several fields of science and technology that are too ambitious for legacy institutions to support. From molecular nanotechnology, to brain-computer interfaces, space exploration, cryptocommerce, and AI, Foresight gathers leading minds to advance research and accelerate progress toward flourishing futures.

We are entirely funded by your donations. If you enjoy what we do please consider donating through our donation page: https://foresight.org/donate/

Visit https://foresight.org, subscribe to our channel for more videos or join us here:

• Twitter: https://x.com/foresightinst

• Facebook: https://www.facebook.com/foresightinst

• LinkedIn: https://www.linkedin.com/company/foresight-institute