Device and method for training a neuronal network
US12248878B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 19, 2021 |
| Grant date | Mar 11, 2025 |
| Priority date | — |
| Expiry date | Dec 28, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG05D2101/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for training a neural network. The neural network comprises a first layer which includes a plurality of filters to provide a first layer output comprising a plurality of feature maps. Training of the classifier includes: receiving, by a preceding layer, a first layer input in the first layer, wherein the first layer input is based on the input signal; determining the first layer output based on the first layer input and a plurality of parameters of the first layer; determining a first layer loss value based on the first layer output, wherein the first layer loss value characterizes a degree of dependency between the feature maps, the first layer loss value being obtained in an unsupervised fashion; and training the neural network. The training includes an adaption of the parameters of the first layer, the adaption being based on the first layer loss value.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.