MahmudulAlam/Holographic-Reduced-Representations
Holographic Reduced Representations
This project helps researchers and machine learning practitioners work with Holographic Reduced Representations (HRR). It allows you to combine abstract concepts or data using 'binding' operations on numerical vectors and later retrieve individual components using 'unbinding'. This is useful for tasks involving compositional structures and distributed representations, like creating complex knowledge representations or secure computing with neural networks.
Use this if you need to represent complex relationships between different pieces of information in a compact, distributed way, and require the ability to retrieve individual components from these combined representations.
Not ideal if your primary goal is simple vector similarity searches or if you don't require the compositional and reconstructive properties of Holographic Reduced Representations.
Stars
30
Forks
8
Language
Python
License
MIT
Category
Last pushed
Dec 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MahmudulAlam/Holographic-Reduced-Representations"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/