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
Hyperdimensional computing with statistical guarantees: calibrated probabilities, conformal prediction sets, anomaly detection with a guaranteed false-positive rate
Hyperdimensional Computing Library for building Vector-Symbolic Architectures in Python 3
Boolean Hypervectors with various operators for experiments in hyperdimensional computing (HDC).
SWIR hyperspectral sensing for denied-environment ISR and materials discrimination. UAV-mounted 400-2500 nm imaging with edge-deployed CNN/SNN inference for contaminant detection and terrain/materials characterization in austere, offline environments.
Nazgul is a unified C++/Python framework for time-optimal multi-joint trajectory planning (inherited from LongTermPlanner) and edge-efficient hyperdimensional computing (imported from Arthedain), providing a VSA backend factory with 8 algebras, HDC energy analysis at 45nm CMOS
HDC-X: A Hyperdimensional Computing Framework for Efficient Classification on Low-Power Devices
Holographic vectors you can compute with. Bind structure, bundle sets, unbind components cross NumPy, PyTorch, and JAX.
Repository for HYPERDOA: Robust and Efficient DoA Estimation using Hyperdimensional Computing
Contributions to my area of research as a research assistant at ULL in Hyperdimensional Computing (HDC)
Effectively unlimited long-term memory for any LLM - zero context tokens, zero weight updates, cryptographic forgetting certificate.
Sub-linear knowledge retrieval via quantum-inspired hyperdimensional folded space (0.88ms @ 100% accuracy)
Training-free behavioral anomaly detector for Mantle DeFi. HDC engine + Z.ai explainability. Zero false positives, on-chain proof.
Self‑healing, self‑learning, sovereign AI development engine Runs offline on a laptop or tablet. No cloud, no subscription, forever.
HDCpy: An easy-to-use Python library for Hyperdimensional Computing (HDC) research.
PRISM is a neural-free cognitive architecture for knowledge reasoning based on Vector Symbolic Architectures (VSA). Unlike large language models with billions of parameters, PRISM performs complex reasoning through algebraic operations on high-dimensional vectors.
Implementation of a multi-class maximum-margin hyperdimensional computing (HDC) classifier
Cognitive engine based on Hyperdimensional Computing (HDC) and Vector Symbolic Architectures (VSA) for deterministic reasoning in B^100,000 space.
Examples of MNIST classifier using hyperdimentional 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."