US 12,248,878 B2
Device and method for training a neuronal network
Jorn Peters, Amsterdam (NL); Thomas Andy Keller, Amsterdam (NL); Anna Khoreva, Stuttgart (DE); Max Welling, Amsterdam (NL); and Priyank Jaini, Amsterdam (NL)
Assigned to ROBERT BOSCH GMBH, Stuttgart (DE)
Filed by Robert Bosch GmbH, Stuttgart (DE)
Filed on Feb. 19, 2021, as Appl. No. 17/180,383.
Claims priority of application No. 20162157 (EP), filed on Mar. 10, 2020.
Prior Publication US 2021/0287093 A1, Sep. 16, 2021
Int. Cl. G06N 3/082 (2023.01); G05D 1/00 (2024.01); G06F 18/2413 (2023.01); G06N 3/008 (2023.01); G06N 3/04 (2023.01); G06N 3/045 (2023.01); G06N 3/088 (2023.01)
CPC G06N 3/082 (2013.01) [G06F 18/2414 (2023.01); G06N 3/04 (2013.01); G06N 3/045 (2023.01); G06N 3/088 (2013.01); G05D 1/0088 (2013.01); G06N 3/008 (2013.01)] 11 Claims
OG exemplary drawing
 
1. A method for training a neural network, the neural network including a first layer, the first layer including a plurality of filters to provide a first layer output, the first layer output including a plurality of feature maps, the method comprising the following steps:
receiving, from 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 of the first layer output, the first layer loss value being obtained in an unsupervised fashion; and
training the neural network, including adapting the parameters of the first layer, the adaption being based on the first layer loss value.