Patent · US Active

Training a neural network adapter

US10832407B2 · kind B2 · utility

0Cited by
1References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 6, 2019
Grant dateNov 10, 2020
Priority date
Expiry dateMay 22, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In some examples, a system for training a neural network can include a processor to detect a trained neural network application. The processor can also detect a set of images, wherein the neural network application is not trained with the set of images. Additionally, the processor can train an adapter network based on the trained neural network application and the set of images, wherein the adapter network is to be trained by freezing weights of the trained neural network and modifying weights of the adapter network. Furthermore, the processor can use the trained adapter network to process at least one additional image, the processed additional image to be transmitted to the trained neural network to generate an output signal.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.