Patent · US Active

Embedding constrained and unconstrained optimization programs as neural network layers

US12001961B2 · kind B2 · utility

0Cited by
2References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 12, 2022
Grant dateJun 4, 2024
Priority date
Expiry dateDec 12, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/01
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Aspects discussed herein may relate to methods and techniques for embedding constrained and unconstrained optimization programs as layers in a neural network architecture. Systems are provided that implement a method of solving a particular optimization problem by a neural network architecture. Prior systems required use of external software to pre-solve optimization programs so that previously determined parameters could be used as fixed input in the neural network architecture. Aspects described herein may transform the structure of common optimization problems/programs into forms suitable for use in a neural network. This transformation may be invertible, allowing the system to learn the solution to the optimization program using gradient descent techniques via backpropagation of errors through the neural network architecture. Thus these optimization layers may be solved via operation of the neural network itself.

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