Method and apparatus of learning neural network via hierarchical ensemble learning

This invention describes a method for training a neural network. It works by selectively turning off certain processing units, called "feature detectors," within the network's first layer. It then also disables other connected processing units, potentially in a subsequent layer. The remaining active units are then updated using a standard learning algorithm called gradient descent.

Why it matters: The classification includes distributed learning, which was less prevalent in 2015. This method of selectively disabling network components could offer new efficiencies for training the much larger and more complex neural networks common today, especially in distributed or federated learning environments.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedSoftware logic, nothing to manufacture

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.

This one

+10