Patent · US Active

Learning apparatus and method for learning a model corresponding to a function changing in time series

US10783452B2 · kind B2 · utility

2Cited by
0References
25Claims
0Family size

Assignee

Inventor

Key dates

Filing dateApr 28, 2017
Grant dateSep 22, 2020
Priority date
Expiry dateMar 30, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A computer-implemented method is provided for learning a model corresponding to a target function that changes in time series. The method includes acquiring a time-series parameter that is a time series of input parameters including parameter values expressing the target function. The method further includes propagating propagation values, which are obtained by weighting parameters values at time points before one time point according to passage of the time points, to nodes in the model associated with the parameter values at the one time point. The method also includes calculating a node value of each node using each propagation value propagated to each node. The method additionally includes updating a weight parameter used for calculating the propagation values propagated to each node, using a difference between the target function at the one time point and a prediction function obtained by making a prediction from the node values of the nodes.

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