Patent · US Active

Using a neural network

US11468323B2 · kind B2 · utility

0Cited by

2References

13Claims

0Family size

Assignee

KONINIKLIJKE PHILIPS N.V. · NL

Inventors

Vlado Menkovski · Eindhoven, NL
Asif Rahman · Brookline, US
Caroline Denise Francoise Raynaud · Paris, FR
Bryan Conroy · Franklin Square, US
Dimitrios Mavroeidis · Utrecht, NL
Erik Bresch · Eindhoven, NL
Teun Van Den Heuvel · Waalre, NL

Key dates

Filing date	Oct 16, 2018
Grant date	Oct 11, 2022
Priority date	—
Expiry date	Oct 4, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06N20/00
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method, system and computer-program product for identifying neural network inputs for a neural network that may have been incorrectly processed by the neural network. A set of activation values (of a subset of neurons of a single layer) associated with a neural network input is obtained. A neural network output associated with the neural network input is also obtained. A determination is made as to whether a first and second neural network input share similar sets of activation values, but dissimilar neural network outputs or vice versa. In this way a prediction can be made as to whether one of the first and second neural network inputs has been incorrectly processed by the neural network.

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