US 12,468,942 B2
Method for training and/or verifying a robustness of an artificial neural network
Frank Schmidt, Leonberg (DE)
Assigned to ROBERT BOSCH GMBH, Stuttgart (DE)
Filed by Robert Bosch GmbH, Stuttgart (DE)
Filed on Jul. 21, 2022, as Appl. No. 17/869,979.
Claims priority of application No. 10 2021 208 520.2 (DE), filed on Aug. 5, 2021.
Prior Publication US 2023/0039379 A1, Feb. 9, 2023
Int. Cl. G06N 3/08 (2023.01); B60W 40/02 (2006.01); G06N 3/082 (2023.01); G06V 10/44 (2022.01); G06V 10/74 (2022.01); G06V 10/764 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01); G06V 20/58 (2022.01); H04N 19/85 (2014.01)
CPC G06N 3/08 (2013.01) [G06V 10/761 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); B60W 40/02 (2013.01); G06N 3/082 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 20/56 (2022.01); G06V 20/58 (2022.01); H04N 19/85 (2014.11)] 14 Claims
OG exemplary drawing
 
1. A method for training and/or verifying a robustness of an artificial neural network in which the artificial neural network is configured to determine an output variable, the method comprising the following steps:
predefining an input variable for the artificial neural network that has a plurality of dimensions, for each dimension of the input variable or for each dimension of an output of a linear layer of the artificial neural network without an activation function to which the input variable is mapped by the artificial neural network, performing:
determining an upper input variable limit for which a disturbance model by which the input variable is able to be mapped to a disturbed input variable has a highest possible value in the dimension, and
determining a lower input variable limit for which the disturbance variable model has a lowest possible value in the dimension;
for each dimension of the output variable, performing:
determining a lower output variable limit for the output variable with values from a value range restricted by the lower input variable limits and the upper variable limits, and
determining an upper output variable limit for the output variable with the values from the value range restricted by the upper input variable limits and the lower input variable limits;
determining a lowest possible value of a real-valued function with values from a value range restricted by the lower output variable limit and the upper output variable limit;
determining a highest possible value of the real-valued function with values from the value range restricted by the lower output variable limit and the upper output variable limit; and
determining an output that confirms a robustness of the network when the lowest possible value and the highest possible value lie within a predefined interval of permissible values.