Hrrformer: A Neuro-symbolic Self-attention Model (ICML23)
Holographic Reduced Representations
A Walsh Hadamard Derived Linear Vector Symbolic Architecture 🔥
HGConv: Holographic Global Convolutional Networks
Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations
Research code for heuristically hiding information for inference run on 3rd party systems (ICML 22)
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.
Correctness-first PyTorch EBMs with FFT circulant layers, tiled Triton mixing, differentiable and Householder transforms, HRR formal-state search, Langevin sampling, and reproducible benchmarks.
An auditable, hallucination-free alternative to LLMs: 100k facts, sub-millisecond queries, one CPU thread. HRR/VSA substrate with provenance, calibrated confidence, and belief revision. Every benchmark reproducible from the repo.
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."