Patent · US Active

Machine-learning-based architecture search method for a neural network

US12175350B2 · kind B2 · utility

0Cited by
2References
25Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 10, 2019
Grant dateDec 24, 2024
Priority date
Expiry dateJun 26, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/047
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In at least one embodiment, differentiable neural architecture search and reinforcement learning are combined under one framework to discover network architectures with desired properties such as high accuracy, low latency, or both. In at least one embodiment, an objective function for search based on generalization error prevents the selection of architectures prone to overfitting.

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