Vorrichtung, Datenstruktur und Verfahren zur Abstimmung von Gewichten eines Neuronalen Netzes eines Modells

Details

Veröffentlichungs-Nr.

EP4718285

Anmeldetag

25. September 2024

Veröffentlichung

1. April 2026

Rechtsraum

EP

IPC

G06F16/906, G06N3/00

Abstract

Device (100), data structure, and method for tuning weights of a neural network of a model (106) for processing input of the model (106) in particular comprising or representing information about a technical system (108) and outputting an output of the model (106) in particular for operating a technical system (108), wherein the model (106) comprises an in particular linear layer for mapping a multidimensional input of the layer depending on the weights to a multidimensional output of the layer, wherein the model (106) is configured to determine the input of the layer depending on the input of the model (106), wherein the model (106) is configured to determine the output of the model (106) depending on the output of the layer, wherein the method comprises providing training data comprising the input of the model (106) and a ground truth for the output of the model (106) corresponding to the input of the model (106) in the training data, providing a set of tuning methods for tuning the weights, determining the principal components decomposition of a weight matrix comprising the weights, wherein the principal component decomposition comprises a matrix formed by the eigenvectors of the covariance matrix of the weight matrix, determining the eigenvalues of the covariance matrix corresponding to the eigenvectors, rearranging the eigenvectors in the matrix in an order resulting in a monotonically decreasing order of the eigenvalues that are associated with the eigenvectors, rearranging the weights in the weight matrix according to the order in that the eigenvectors are rearranged in the matrix, partitioning the weight matrix into groups of weights, associating at least one group of the groups with a method of tuning selected from the set of tuning methods, and tuning the weights in the at least one group on the training data with the tuning method, in particular leaving at least one group of the groups unaltered in the tuning.

Anmelder

Firma

Robert Bosch GmbH

Land

🇩🇪 Deutschland