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
Cognitive Computing with Associative Memory
Hyperdimensional Computing Library for building Vector-Symbolic Architectures in Python 3
GPU-accelerated neural network operations using Vulkan compute shaders.
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.
Repository for HYPERDOA: Robust and Efficient DoA Estimation using Hyperdimensional Computing
Hyperprobe is the Python implementation of the framework proposed in the paper "Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures".
"VSA, Analogy, and Dynamic Similarity" presentation given at the Workshop on Developments in Hyperdimensional Computing and Vector Symbolic Architectures, Heidelberg, Germany, 2020-03-16.
Composition-episodic cognitive memory for AI agents (VSA + lattice geometry)
Publications by Peter Overmann
Deterministic logical reasoning engine using Vector Symbolic Architectures. 100% ProofWriter. CPU-only. No backprop.
Keynote presentation for the Midnight Sun Workshop on Vector Symbolic Architectures
A quantum Hyper-Dimensional Computing (qHDC) framework in Qiskit.
This project aims to develop a very basic Vector Symbolic Architecture model to use as a default model in my other VSA projects.
Cognitive engine based on Hyperdimensional Computing (HDC) and Vector Symbolic Architectures (VSA) for deterministic reasoning in B^100,000 space.
Hyperdimensional Computing classifier for Human Activity Recognition -BSc dissertation, Cardiff University
Interpretable hyperdimensional computing for language identification, built on torchhd. 97% accuracy across 21 languages, with prototype decomposition showing why.
Source code of the slides for the lecture "Analogical Reasoning" given on 2021-10-06 as Module 6 of Neuroscience 299: Computing with High-Dimensional Vectors at the Redwood Center for Theoretical Neuroscience, University of California, Berkeley
A high-performance Rust and WebGPU engine that compiles and executes experimental logic at hardware speed.
Add a description, image, and links to the vector-symbolic-architectures topic page so that developers can more easily learn about it.
To associate your repository with the vector-symbolic-architectures topic, visit your repo's landing page and select "manage topics."