Patent · US Active

Training network to minimize worst-case error

US11475310B1 · kind B1 · utility

4Cited by
10References
22Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 28, 2017
Grant dateOct 18, 2022
Priority date
Expiry dateFeb 24, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/048
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Some embodiments provide a method for configuring a machine-trained (MT) network that includes multiple configurable weights to train. The method propagates a set of inputs through the MT network to generate a set of output probability distributions. Each input has a corresponding expected output probability distribution. The method calculates a value of a continuously-differentiable loss function that includes a term approximating an extremum function of the difference between the expected output probability distributions and generated set of output probability distributions. The method trains the weights by back-propagating the calculated value of the continuously-differentiable loss function.

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