Consilient Network· The graph of everyone who built this · Add your entry ↗
Outreach path

Feature vectors, manifolds, and the metric of trust: the geometry AI rediscovered

Modern AI's deepest design principles — the manifold hypothesis, metrics on latent spaces, hyperbolic embeddings, equivariance — are one lesson learned repeatedly: meaning is what survives coordinate change. Hare learned that lesson in APL at Berkeley in the 1980s, was handed back-propagation by his advisor, and built the constructive version: a metric for coordination space, specified rather than learned, enforced rather than observed.

7 stopsFor: AI researchers, the geometric deep learning community, and anyone who has read Hinton latelyAll paths
His advisors handed him Hinton's back-propagation paper and showed him a network running on a NeXT machine. Forty years later the field converged on the geometry he was already working in — and the architecture is that geometry made enforceable.
The path

Follow it in order

Each stop is a page in the graph. The order is an argument — but every one of them is also a door into the rest of it, so you can leave the path wherever it stops being useful.

Where it lands

What the path is for

The point

Geometric deep learning constrains a network so that only symmetry-respecting transformations are expressible. The architecture constrains the substrate so that only governance-preserving derivations settle. Same mathematics, opposite direction — the field discovers geometry, the architecture specifies it. A reviewer who accepts the first has already accepted the formal basis of the second. And the widest-register statement of the same geometry now exists: One Mathematics, Many Heavens — the unification of all faiths and science — running the identical Hilbert-space argument from the IEOR classroom to the Fermi Paradox, with its claims graded in a closing ledger.

Add to this record → Other paths →

Share this
← PreviousAll paths
+ Add to the record