Can a compiler spend HDC's accuracy budget? Reviewing ApproxHDC
How ApproxHDC searches application, compiler, and simulated-hardware choices to trade HDC task quality for speed and energy efficiency, and what the reported evidence establishes.
Blog
Blog Archive
Every post from HDC Labs, collected in one place, newest first.
All posts
Showing 16–20 of 26 posts
Why connected data needs associative search
Graph search follows exact relationships, while associative search finds similar situations from incomplete examples.
Can hypervectors learn the hardware they run on?
How learnable HDC encoders can adapt similarity geometry to modeled compute-in-memory nonlinearities, and what the current evidence establishes.
How HDC complements deep learning
Why the future of AI may be hybrid: deep learning learns powerful representations, while HDC complements it with compositional operations, associative memory, and lightweight adaptation.
What does an HDC graph encoder remember? Reviewing GraphHD-Order
A close look at what GraphHD and GraphHD-Order preserve, what the reported results establish, and what the released implementation leaves unresolved.
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.