Verfahren und System zur Lokalen Erklärbarkeit eines Neuronalen Netzwerkvorhersagefeldes

Details

Veröffentlichungs-Nr.

EP4198836

Aktenzeichen

EP22212969

Anmeldetag

13. Dezember 2022

Veröffentlichung

21. Juni 2023

Rechtsraum

EP

IPC

G06N5/045G06N3/04

Abstract

A network output is generated by feeding an input vector to an input layer of a neural network model having a plurality of neurons arranged in a sequence of layers, a plurality of neuron weights, and a plurality of neuron biases. The network output is used to determine an output relevance score. Relevance scores at a last layer of the sequence of layers are generated. Relevance scores are obtained at a first layer of the sequence of layers by reverse propagating the relevance scores generated at the last layer through the sequence of layers other than the last layer using the neuron weights and neuron biases. A feature relevance vector is formed based on the input vector and the relevance scores obtained at the first layer and included in a local explainability dataset, which is then used to generate a local explanation of a prediction of the neural network model.

Anmelder

Firma

SAP SE

Land

🇩🇪 Deutschland

Fachgebiete