P158Filed

Ternary Machine Learning for Autonomous Systems

Metadata hidden inside the weight stream itself — the unused fourth bit-pattern carries configuration.

AU Application
2023900158
Filing Date
1 April 2025
Index Number
P158
Figures
18 figures
Batch / Category
Capstone

Explore the Vision

Discover this technology through five complementary perspectives — from technical architecture to partnership outcomes. Each layer reveals a different aspect of how this innovation creates value.

Metadata hidden inside the weight stream itself — the unused fourth bit-pattern carries configuration.

What It IS

Technical Vision

The architectural essence — what makes this technology work

A stream of packed ternary weights — 00, 01, 10 encoding the three values — with the unused pattern 11 serving as an escape code for embedded metadata. Provenance, configuration, and integrity markers woven directly into the weight data. Self-describing neural network weights.

1/5
Explore the buyer's journey across 5 perspectives

Abstract

Comprehensive system integrating all ternary technologies (NPU, agents, confidence, security) for general autonomous system deployment.

Visual Essence

A stream of packed ternary weights — 00, 01, 10 encoding the three values — with the unused pattern 11 serving as an escape code for embedded metadata. Provenance, configuration, and integrity markers woven directly into the weight data. Self-describing neural network weights.

Visual Family:silicon-seal

Technology Domains

Related Patents

From the silicon-seal visual family