Hrrformer: A Neuro-symbolic Self-attention Model (ICML23)
-
Updated
Oct 8, 2025 - Python
Hrrformer: A Neuro-symbolic Self-attention Model (ICML23)
Holographic Reduced Representations
A Walsh Hadamard Derived Linear Vector Symbolic Architecture 🔥
HGConv: Holographic Global Convolutional Networks
Research code for heuristically hiding information for inference run on 3rd party systems (ICML 22)
Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations
Persistent memory graph for AI coding agents — semantic search, knowledge graph, and time-based decay over MCP
A structured vector memory system for AI agents using Holographic Reduced Representations (HRR). Encodes relational facts into fixed-width vectors via circular convolution, retrieves through algebraic probes. Fully local — FastAPI, NumPy, SQLite, Next.js.
Resonant Cognitive Kernel: an auditable, hallucination-free reasoning system built on hyperdimensional computing. Reasons via explicit chains, learns by deriving (not retraining), runs on CPU. MIT licensed, 714 tests.
Add a description, image, and links to the hrr topic page so that developers can more easily learn about it.
To associate your repository with the hrr topic, visit your repo's landing page and select "manage topics."