Nybble™
Library

Research Library

Patent2016

System and method for addressing overfitting in a neural network

Google LLC · USPTO — US9406017B2 · 2016

Abstract

Covers a training method that randomly omits units from a neural network on each pass, so no unit can rely on any particular other one being present, and averages over the resulting ensemble of thinned networks at prediction time. The claims cover the selective-omission procedure and its use during training.

Why it matters

Dropout, patented. Worth a look because it is one of the clearest cases of a technique that spread through the field as a free idea while also existing as an enforceable claim.

patenttrainingarchitecture
Read the source

https://patents.google.com/patent/US9406017B2/en

About Nybble™

The AI space moves fast.
Nybble™ is how you keep up — and stay sharp.

Snack

What happened. In two minutes.

The AI news cycle moves at a pace no one can keep up with. Snack distills what launched, what shipped, and what matters — every day, without the filler.

Go to Snack
Stack

The concepts behind the headlines.

News tells you what. Stack tells you why and how. From RAG architectures to agentic evals, these are the ideas that will shape what you build next.

Go to Stack
Hack

Prove you actually get it.

Reading about LangChain is not the same as knowing it. Hack challenges you with production-grade questions, then shows you the references that make the answer stick.

Go to Hack