Patent · US Active

Configuring a neural network for equivariant or invariant behavior

US12164302B2 · kind B2 · utility

0Cited by
0References
11Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 20, 2022
Grant dateDec 10, 2024
Priority date
Expiry dateMar 21, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N7/01
  • WIPO fieldControl
  • WIPO sectorInstruments

Abstract

A method for configuring a neural network which is designed to map measured data to one or more output variables. The method includes: transformation(s) of the measured data is/are specified which when applied to the measured data, is/are meant to induce the output variables supplied by the neural network to exhibit an invariant or equivariant behavior; at least one equation is set up which links a condition that the desired invariance or equivariance be given with the architecture of the neural network; by solving the at least one equation a feature is obtained that characterizes the desired architecture and/or a distribution of weights of the neural network in at least one location of this architecture; a neural network is configured in such a way that its architecture and/or its distribution of weights in at least one location of this architecture has/have all of the features ascertained in this way.

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