Configuring a neural network for equivariant or invariant behavior
US12164302B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 20, 2022 |
| Grant date | Dec 10, 2024 |
| Priority date | — |
| Expiry date | Mar 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.