Torchhd is a Python library for Hyperdimensional Computing and Vector Symbolic Architectures
-
Updated
Jun 19, 2025 - Python
Torchhd is a Python library for Hyperdimensional Computing and Vector Symbolic Architectures
The Fuzzy-Pattern Tsetlin Machine library, with zero external dependencies, performs blazingly fast.
Cognitive Computing with Associative Memory
Accelerator for Hyperdimensional Computing (HDC)
Hyperdimensional Computing Library for building Vector-Symbolic Architectures in Python 3
Hyperdimensional computing with statistical guarantees: calibrated probabilities, conformal prediction sets, anomaly detection with a guaranteed false-positive rate
Boolean Hypervectors with various operators for experiments in hyperdimensional computing (HDC).
An automated HDC platform
A collection of Hyperdimensional Computing (HDC) models implemented in C++
HDC-X: A Hyperdimensional Computing Framework for Efficient Classification on Low-Power Devices
A Rust library for hyperdimensional computing (HDC)
A chef's palate for AI agent memory; Un-mix any day's work into its exact projects, and detect workstreams nobody has named yet. Hyperdimensional fingerprints, zero dependencies.
A library for training and running HDC models on embedded devices.
Holographic vectors you can compute with. Bind structure, bundle sets, unbind components cross NumPy, PyTorch, and JAX.
A high-performance autonomous bitwise model leveraging Vector Symbolic Architectures (VSA) and Hyperdimensional Computing (HDC). Built in Rust.
Repository for HYPERDOA: Robust and Efficient DoA Estimation using Hyperdimensional Computing
Software that builds itself, pays for its own inference, and gets better with every run.
An extended note on using Vector Symbolic Architectures to implement Next Generation Reservoir Computing
Add a description, image, and links to the hyperdimensional-computing topic page so that developers can more easily learn about it.
To associate your repository with the hyperdimensional-computing topic, visit your repo's landing page and select "manage topics."