公开(公告)号：US12100197B2

公开(公告)日：2024-09-24

申请号：US17610669

申请日：2020-06-10

申请人： Robert Bosch GmbH

发明人： Lydia Gauerhof ,  Nianlong Gu

IPC分类号： G06V10/82 ,  G06N3/045 ,  G06N3/088 ,  G06V10/764

CPC分类号： G06V10/82 ,  G06N3/045 ,  G06N3/088 ,  G06V10/764

摘要： A method for training a machine learning system. The method includes generating an augmented dataset including input images for training the machine learning system, which is for classification and/or semantic segmentation of input images, using a first machine learning system, which is embodied as a decoder of an autoencoder, and a second machine learning system, which is embodied as an encoder of the autoencoder. Latent variables are ascertained from the input images using the encoder. The input images are classified as a function of ascertained feature characteristics of their image data. An augmented input image of the augmented dataset is ascertained from at least one of the input images as a function of average values of the ascertained latent variables in at least two of the classes. The image classes are selected so that the input images classified therein agree in their characteristics in a predefinable set of other features.

公开(公告)号：US20240281655A1

公开(公告)日：2024-08-22

申请号：US18443711

申请日：2024-02-16

申请人： Robert Bosch GmbH

发明人： Lydia Gauerhof ,  Bangyu Zhu ,  Christoph Schorn

IPC分类号： G06N3/08

CPC分类号： G06N3/08

摘要： A method for training a measurement network which ascertains the uncertainty of an already trained task network. In the method: each training record of measurement data from a training data set is fed to a plurality of modifications of a deterministic task network, or fed multiple times to a probabilistic task network, and thus mapped onto a plurality of outputs; each training record is fed to the measurement network and mapped onto a prediction of the distribution of the plurality of outputs, wherein the processing chain of the measurement network includes a part of the processing chain of the task network; a predefined cost function evaluates the extent to which the prediction of the distribution is consistent with the outputs; and network parameters which characterize the behavior of that part of the measurement network that does not belong to the processing chain of the task network are optimized.

公开(公告)号：US20220222929A1

公开(公告)日：2022-07-14

申请号：US17596126

申请日：2020-06-10

申请人： Robert Bosch GmbH

发明人： Lydia Gauerhof ,  Nianlong Gu

IPC分类号： G06V10/774 ,  G06V10/82 ,  G06N3/04

摘要： A computer-implemented neural network system including a first machine learning system, in particular a first neural network, a second machine learning system, in particular a second neural network, and a third machine learning system, in particular a third neural network. The first machine learning system is designed to ascertain a higher-dimensional constructed image from a predefinable low-dimensional latent variable. The second machine learning system is designed to ascertain the latent variable again from the higher-dimensional constructed image, and the third machine learning system is designed to distinguish whether or not an image it receives is a real image.

公开(公告)号：US12125268B2

公开(公告)日：2024-10-22

申请号：US17596126

申请日：2020-06-10

申请人： Robert Bosch GmbH

发明人： Lydia Gauerhof ,  Nianlong Gu

IPC分类号： G06V10/774 ,  G06N3/045 ,  G06V10/82

CPC分类号： G06V10/7747 ,  G06N3/045 ,  G06V10/82

摘要： A computer-implemented neural network system including a first machine learning system, in particular a first neural network, a second machine learning system, in particular a second neural network, and a third machine learning system, in particular a third neural network. The first machine learning system is designed to ascertain a higher-dimensional constructed image from a predefinable low-dimensional latent variable. The second machine learning system is designed to ascertain the latent variable again from the higher-dimensional constructed image, and the third machine learning system is designed to distinguish whether or not an image it receives is a real image.

公开(公告)号：US20210089911A1

公开(公告)日：2021-03-25

申请号：US17041798

申请日：2019-04-02

申请人： Robert Bosch GmbH

发明人： Christoph Schorn ,  Jaroslaw Topp ,  Lydia Gauerhof ,  Stefan Gehrer

IPC分类号： G06N3/08 ,  G06N3/063 ,  G06F11/07

摘要： A method for controlling an actuator. The method includes: mapping parameters of a trained machine learning system that have a magnitude from a first set of different possible magnitudes to a magnitude of at least one predefinable second set of different possible magnitudes; storing the converted parameters in a memory block in each case; ascertaining an output variable of the machine learning system as a function of an input variable and the stored parameters. The stored parameters are read out from the respective memory block with the aid of at least one mask. The actuated is actuated as a function of the ascertained output variable. A computer system, a computer program, and a machine-readable memory element in which the computer program is stored are also described.

公开(公告)号：US20210072397A1

公开(公告)日：2021-03-11

申请号：US17009351

申请日：2020-09-01

申请人： Robert Bosch GmbH

发明人： Jan Niklas Caspers ,  Jasmin Ebert ,  Lydia Gauerhof ,  Michael Pfeiffer ,  Remigius Has ,  Thomas Maurer ,  Anna Khoreva

IPC分类号： G01S17/894 ,  G01S17/931

摘要： A generator for generating three-dimensional point clouds of synthetic LIDAR signals from a set of LIDAR signals measured with the aid of a physical LIDAR sensor. The generator includes a random generator and a first machine learning system, which receives vectors or tensors of random values from the random generator as input, and maps each such vector, or each such tensor, onto a three-dimensional point cloud of a synthetic LIDAR signal with the aid of an internal processing chain. The internal processing chain of the first machine learning system is parameterized by a plurality of parameters which are set in such a way that the three-dimensional point cloud of the LIDAR signal, and/or at least one characteristic variable derived from this point cloud, essentially has/have the same distribution for the synthetic LIDAR signals as for the measured LIDAR signals.

公开(公告)号：US20230086980A1

公开(公告)日：2023-03-23

申请号：US17940851

申请日：2022-09-08

申请人： Robert Bosch GmbH

发明人： Lydia Gauerhof ,  Andreas Albrecht ,  Moritz Hoersch

IPC分类号： G06N20/20

摘要： A method for generating a data set for training and/or testing a machine learning algorithm. The method includes: providing a first data set, wherein the first data set comprises data potentially relevant to the machine learning algorithm, providing an ensemble of data filters, configuring each data filter of the ensemble of data filters on the basis of requirements of the machine learning algorithm, and selecting the first data set by filtering the first data set by means of at least a part of the configured data filters of the ensemble of data filters in order to obtain data for training and/or testing the machine learning algorithm, wherein the data form the data set for training and/or testing the machine learning algorithm.

公开(公告)号：US20220343158A1

公开(公告)日：2022-10-27

申请号：US17658323

申请日：2022-04-07

申请人： Robert Bosch GmbH

发明人： Christoph Schorn ,  Lydia Gauerhof

IPC分类号： G06N3/08 ,  G06K9/62

摘要： A method for detecting whether an input variable for a machine learning system is suitable as an additional training datum or test datum for the machine learning system for retraining and testing. The method includes: processing a detected input variable by way of the machine learning system, intermediate results which are ascertained during the processing of the input variable by the machine learning system being stored; processing the stored intermediate results by way of an anomaly detector, the anomaly detector outputting an output variable which characterizes whether the detected input variable associated with the intermediate results yields an anomalous behavior of the machine learning system; based on the output variable of the network, the input variable of the network and the additional input variables defined as relevant are stored/selected. A computer system, computer program, and a machine-readable memory element on which the computer program is stored are also described.

公开(公告)号：US20220245932A1

公开(公告)日：2022-08-04

申请号：US17610669

申请日：2020-06-10

申请人： Robert Bosch GmbH

发明人： Lydia Gauerhof ,  Nianlong Gu

IPC分类号： G06V10/82 ,  G06N3/04 ,  G06N3/08 ,  G06V10/764

摘要： A method for training a machine learning system. The method includes generating an augmented dataset including input images for training the machine learning system, which is for classification and/or semantic segmentation of input images, using a first machine learning system, which is embodied as a decoder of an autoencoder, and a second machine learning system, which is embodied as an encoder of the autoencoder. Latent variables are ascertained from the input images using the encoder. The input images are classified as a function of ascertained feature characteristics of their image data. An augmented input image of the augmented dataset is ascertained from at least one of the input images as a function of average values of the ascertained latent variables in at least two of the classes. The image classes are selected so that the input images classified therein agree in their characteristics in a predefinable set of other features.

公开(公告)号：US20200049081A1

公开(公告)日：2020-02-13

申请号：US16340527

申请日：2017-10-02

申请人： Robert Bosch GmbH

发明人： Lydia Gauerhof ,  Heiko Fahrion ,  Magnus Oppelland

IPC分类号： F02D35/02 ,  F02D41/00 ,  F02D41/28 ,  G01M15/04

摘要： A method for ascertaining whether a combustion process is being carried out in a cylinder of an internal combustion engine, it being decided whether or not the combustion process is present as a function of a relative angle between a characteristic signature of a variable characterizing a time curve of a state variable of the internal combustion engine and a specifiable crankshaft angle.