What can we recover from a bundled hypervector?
Five MAP experiments explore how bundled hypervectors support semantic retrieval, explainable scores, query preferences, and removal of known facts.
Blog
Blog Archive
Every post from HDC Labs, collected in one place, newest first.
All posts
Showing 11–15 of 26 posts
A category is something a system does
What a new neuroscience framework proposes about context, compression, and action, and how HDC could turn those ideas into a computational architecture.
Does HDC fit the physics of light? Reviewing PhotoHDC
A critical review of PhotoHDC's modeled electro-photonic accelerator, what its evidence supports, and how OLIX and recent optical HDC work sharpen the deployment question.
Do HRR and MAP preserve the same similarity structure?
A reproducible experiment that tests whether HRR and MAP preserve the same similarity structure in a shared encoder.
The (not so surprising) similarities between HDC algebras
How HRR, BSC, and MAP implement the same broad VSA computation shape despite using different hyperspaces and mathematical operations.
Getting started
New to HDC? Start with these four introductions.
Introduction to Hyperdimensional Computing
A gentle introduction to how hyperdimensional computing represents, combines, and retrieves information using high-dimensional hypervectors.
What is a Hypervector?
A closer look at the high-dimensional, distributed mathematical objects that give hyperdimensional computing its unusual geometry.
The Holographic Nature of Hypervectors
How Hyperdimensional Computing distributes information across an entire hypervector, helping representations degrade gradually under noise.
A brief history of vector symbolic architectures
How the problem of representing structured knowledge in distributed systems gave rise to the family now known as HDC and VSA.
Contact
Have a representation problem in mind?
If you're working with connected data, retrieval, agent memory or online learning, we'd love to hear what you're building and where the current representation is falling short.
Get in touch
We usually reply within two business days.