Machine learning US 20,250,328,803 A1 Under examination

Quantum Backpropagation and Dynamic Programming

This invention describes a method for training quantum machine learning models. It works by using quantum bits (qubits) to process data through a quantum circuit. The method then uses a simulated or 'offline' version of this quantum circuit to calculate how to adjust the model's parameters, improving its accuracy. Specifically, the claims narrow the invention to a process involving updating an 'adjoint state' and using a 'tomography algorithm' to refine the model's parameters.

Why it matters: Filed in 2024, quantum computing was still in a nascent stage. Since then, incremental advancements in quantum hardware stability, error correction techniques, or the development of more robust quantum software development kits could make implementing and testing such complex quantum machine learning training methods more practical.

Status: Under examinationA pending application. It has not been granted, and it has not been abandoned.
How hard to build: SpecializedQuantum hardware, quantum software, specialized algorithms

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.

+10