Testing the limits of bundling capacity (2)
How many records fit in a 2,048-dimensional hyperspace before unrelated records start to look alike? Our experiments suggest that the answer depends on how many comparisons we make.
Research
Research perspectives
R&D is a strong focus of our work at HDC Labs. We examine research across HDC, graph intelligence and deep learning, develop our own perspective, and explore how those ideas translate into building practical systems.
Research
Showing 1–10 of 11 posts
Reviewing TrainableHD: What changes when the encoder learns?
How TrainableHD learns its encoder as well as its classes. We follow a mistake through training, work through an incident example, and examine the costs of deployment.
Testing the limits of bundling capacity (1)
What happens as we pack more and more facts into a bundle? We study the limits of bundling capacity with a 50-item questionnaire.
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.
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.
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.
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.
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.
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.