PeterOvermann/TriadicMemory

Cognitive Computing with Associative Memory

41
/ 100
Emerging

Implements tridirectional associative memory on sparse distributed representations (SDRs), enabling one-shot learning and noise-tolerant content-addressable retrieval from incomplete queries. The core Triadic Memory algorithm stores ordered triples of binary hypervectors with cubic capacity scaling: (n/p)³ at dimension n and sparsity p. Provides multi-language implementations (C, Python, Rust, Julia, etc.) and composable circuit primitives for building recurrent architectures like Deep Temporal Memory for temporal pattern recognition.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

37

Forks

14

Language

Mathematica

License

MIT

Last pushed

Feb 11, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PeterOvermann/TriadicMemory"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.