AutoInvent
Turn abandoned patents
into your own filing
Get Started
Patent drawing for System and method using neural networks for analog-to-information processors
US 10,970,441 B1
Computing US 10,970,441 B1 Not in force

System and method using neural networks for analog-to-information processors

This system uses artificial intelligence, specifically neural networks, to automatically design electronic circuits. It creates a mathematical blueprint of a circuit, maps its components to "neurons," and then tests these on a special hardware platform to find the best arrangement. The claims narrow this down to designing analog-to-digital interfaces for mixed-signal circuits, potentially using a resistive random-access memory (RRAM) array as the hardware platform.

Why it matters: Since 2019, neural network capabilities and specialized AI hardware, like RRAM, have matured significantly. This makes the automated design and optimization of complex analog circuits more practical.

Status
Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build
SpecializedNeural network software, circuit design, RRAM hardware

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.