Abstract: A method trains a data-based sensor model for determining a change-point timing in at least one sensor signal of a cyclic technical process executed by a technical system. The method includes providing sensor signal time series of a sampled measured value and an associated change-point timing, and determining an evaluation signal time series by defining a regular evaluation time window over the sensor signal time series. The method further includes determining training datasets having the evaluation signal time series and the assigned change-point timing, and training the data-based sensor model with the training datasets. The change-point timing is provided as a classification vector. The classification vector encodes a time point within the evaluation time window by a position of an element of the classification vector and encodes a time point before and/or after the evaluation time window by a further position of a further element of the classification vector.

Abstract: A method evaluates a trained data-based evaluation model for determining a model output for controlling, regulating, operating, or monitoring a technical system with periodically determined input data sets. The method includes recording input data sets for a predetermined number of time-sequential scanning steps, and aggregating the input data sets into an input data package of validated input data sets. The method further includes determining an evaluation result for each of the input data sets in the input data package using the trained data-based evaluation model. Upon each evaluation, one or more model parameters of the trained data-based evaluation model are reduced by an amount or set to 0. The method is further configured to aggregate the evaluation results to obtain the model output.

Abstract: A method is for generating training data for training a machine learning algorithm. The training data respectively include a data point and a data value associated with the data point. The method includes providing first training data for training the machine learning algorithm and approximating a manifold in which at least one part of the data points of the first training data is located. The method further includes determining a structure of the at least one part of the data points of the first training data in the manifold, and generating additional training data based on the determined structure of the at least one part of the data points of the first training data in the manifold.

Abstract: A method is for generating training data for training a machine learning algorithm. The training data respectively include a data point and a data value associated with the data point. The method includes providing first training data for training the machine learning algorithm, providing an additional data point, and approximating nearest neighbors of the additional data point based on the data points of the first training data. The method further includes determining a data value associated with the additional data point from data values associated with the nearest neighbors of the additional data point. A data pair, including the additional data point and the data value associated with the additional data point, forms additional training data.

Abstract: A method for a plausibility check of the output of an artificial neural network (ANN) utilized as a classifier. The method includes: a plurality of images for which the ANN has ascertained an association with one or multiple classes of a predefined classification, and the association that is ascertained in each case by the ANN, are provided; for each image at least one feature parameter is determined which characterizes the type, the degree of specificity, and/or the position of at least one feature contained in the image; for each combination of an image and an association, a spatially resolved relevance assessment of the image is ascertained by applying a relevance assessment function; a setpoint relevance assessment is ascertained for each combination, using the feature parameter; a quality criterion for the relevance assessment function is ascertained based on the agreement between the relevance assessments and the setpoint relevance assessments.

Abstract: A computer-implemented method for reliably identifying objects in a sequence of input images received with the aid of an imaging sensor, positions of light sources in the respective input image being ascertained from the input images in each case with the aid of a first machine learning system, in particular, an artificial neural network, and objects from the sequence of input images being identified from the resulting sequence of positions of light sources, in particular, with the aid of a second machine learning system, in particular, with the aid of an artificial neural network.

Abstract: A method for ascertaining a depth information image for an input image. The input image is processed using a convolutional neural network, which includes multiple layers that sequentially process the input image, and each converts an input feature map into an output feature map. At least one of the layers is a depth map layer, the depth information image being ascertained as a function of a depth map layer. In the depth map layer, an input feature map of the depth map layer is convoluted with multiple scaling filters to obtain respective scaling maps, the multiple scaling maps are compared pixel by pixel to generate a respective output feature map in which each pixel corresponds to a corresponding pixel from a selected one of the scaling maps.

Abstract: A computer-implemented method for evaluating an image classifier, in which a classifier output of the image classifier is provided for the actuation of an at least semi-autonomous robot. The evaluation method includes: ascertaining a first dataset including image data and annotations being assigned to the image data, the annotations including information about the scene imaged in the respective image and/or about image regions to be classified and/or about movement information of the robot; ascertaining regions of the scenes that are reachable by the robot based on the annotations; ascertaining relevance values for image regions to be classified by the image classifier; classifying the image data of the first image dataset with the aid of the image classifier; evaluating the image classifier based on image regions correctly classified by the image classifier and incorrectly classified image regions, as well as the calculated relevance values of the corresponding image regions.

Abstract: A system and computer-implemented method for training a machine learnable model to estimate a relative scale of objects in an image. A feature extractor and a scale estimator comprising a machine learnable model part are provided. The feature extractor may be pretrained, while the scale estimator may be trained by the system and method to transform feature maps generated by the feature extractor into relative scale estimates of objects. For that purpose, the scale estimator may be trained on training data in a specific yet non-supervised manner which may not require scale labels. During inference, the scale estimator may be applied to several image patches of an image. The resulting patch-level scale estimates may be combined into a scene geometry map which may be indicative of a geometry of a scene depicted in the image.

Abstract: A device and a method, in particular a computer-implemented method, for the verification of an artificial neural network that is trained to map an input point from an input space of a function, in particular a limited or Lipschitz-constant function, as accurately as possible onto a functional value of the function. A test point is specified, the test point including a pair of a test input point from the input space of the function and a test functional value, the input point being determined from the input space, the input point being mapped by the artificial neural network onto the functional value, a reference for the functional value being determined using the test input point, a deviation of the functional value from the reference being determined, and a measure of a susceptibility to error of the artificial neural network being determined as a function of the deviation.

Abstract: A computer-implemented method for ascertaining a closure point in time of an injector of an internal combustion engine using a classifier. The method includes: ascertaining a time series of input signals, each corresponding to a point in time within the time series, and each characterizing a deformation of the injector; ascertaining a plurality of first values using the classifier based on the time series, in each case a first value corresponding to a point in time of the time series, and the first value characterizing a probability that the closure point in time of the injector matches the point in time; ascertaining a plurality of second values, each being a sum of neighboring first values, of a first value and the first value, the second value corresponding to the point in time to which the first value corresponds; ascertaining the closure point in time based on the largest second value.

Abstract: A computer-implemented method for training a data-based point in time determination model for ascertaining an opening or closing point in time of an injection valve of an internal combustion engine, based on a sensor signal. The method includes: providing a set of training data sets from a measurement of the internal combustion engine by scanning the sensor signal of a sensor of the injection valve on a test stand, the training data sets assigning a time indication of the opening or closing point in time to an evaluation point time series; assigning a difficulty value to each training data set; classifying the training data sets into a number of difficulty classes corresponding to their respective difficulty value; ascertaining new training data sets as a function of the training data sets assigned to each difficulty class; training the model with the set of new training data sets.

Abstract: A computer-implemented method for ascertaining a closure point in time of an injector of an internal combustion engine using a classifier. The method includes: ascertaining a time series of input signals, each corresponding to a point in time within the time series, and each characterizing a deformation of the injector; ascertaining a plurality of first values using the classifier based on the time series, in each case a first value corresponding to a point in time of the time series, and the first value characterizing a probability that the closure point in time of the injector matches the point in time; ascertaining a plurality of second values, each being a sum of neighboring first values, of a first value and the first value, the second value corresponding to the point in time to which the first value corresponds; ascertaining the closure point in time based on the largest second value.

Abstract: A computer-implemented method for training a scale-equivariant convolutional neural network. The scale-equivariant convolutional neural network is configured to determine an output signal characterizing a classification of an input image of the scale-equivariant convolutional neural network. The scale-equivariant convolutional neural network includes a convolutional layer. The convolutional layer is configured to provide a convolution output based on a plurality of steerable filters of the convolutional layer and a convolution input. The convolution input is based on the input image and the steerable filters are determined based on a plurality of basis filters. The method for training includes training the plurality of basis filters.

Abstract: A method for recognizing at least one object in at least one input image. In the method, a template image of the object is processed by a first convolutional neural network (CNN) to form at least one template feature map; the input image is processed by a second CNN to form at least one input feature map; the at least one template feature map is compared to the at least one input feature map; it is evaluated from the result of the comparison whether and possibly at which position the object is contained in the input image, the convolutional neural networks each containing multiple convolutional layers, and at least one of the convolutional layers being at least partially formed from at least two filters, which are convertible into one another by a scaling operation.

Abstract: A method for plausibilizing the output of an artificial neural network (ANN) used as classifier. The method includes the following steps: a plurality of images, for which the ANN has determined an assignment to one or more classes of a predetermined classification, as well as the assignment determined in each case by the ANN are provided; for each combination of one image and one assignment, a location-resolved relevance evaluation of the image is determined utilizing a relevance evaluation function, this relevance evaluation indicating which parts of the image have contributed, to what extent, to the assignment; a further classifier is trained to determine from one image and one relevance evaluation ascertained for the image, a reconstruction of the assignment to which this relevance evaluation relates; based on the agreement between the reconstructions and the actual assignments, a figure of merit is determined for the relevance evaluation function.

Abstract: A method for a plausibility check of the output of an artificial neural network (ANN) utilized as a classifier. The method includes: a plurality of images for which the ANN has ascertained an association with one or multiple classes of a predefined classification, and the association that is ascertained in each case by the ANN, are provided; for each image at least one feature parameter is determined which characterizes the type, the degree of specificity, and/or the position of at least one feature contained in the image; for each combination of an image and an association, a spatially resolved relevance assessment of the image is ascertained by applying a relevance assessment function; a setpoint relevance assessment is ascertained for each combination, using the feature parameter; a quality criterion for the relevance assessment function is ascertained based on the agreement between the relevance assessments and the setpoint relevance assessments.

Abstract: A method for parameterizing a machine learning system, in particular a neural network, that is configured to ascertain in each case an associated class of a plurality of classes from input data. The machine learning system is trained once with correctly labeled training data, and once with not correctly labeled training data. Hyperparameters of the machine learning system are selected in such a way that the particular trained machine learning system may reproduce actual classifications of the correctly labeled training data better than actual classifications of the not correctly labeled training data.

Abstract: A computer-implemented method for processing sensor data using a convolutional network. The method includes: processing the sensor data using several successive layers of the convolutional network, which has a convolution filter layer that receives an input matrix having input data values, implements a first filter matrix that is defined by a sum, weighted with a first weighting, of basic filter functions, calculates a second weighting from the first weighting by applying to the first weighting, for a respective value of a transformation parameter, a transformation formula that is parameterized by the transformation parameter, for each second weighting, ascertains a respective second filter matrix by calculating a sum, weighted with the second weighting, of the basic filter functions, and convolutes the input matrix with the first filter matrix and with each of the second filter matrices, so that for each filter matrix, an output matrix having output data values is generated.

Abstract: A method for ascertaining a depth information image for an input image. The input image is processed using a convolutional neural network, which includes multiple layers that sequentially process the input image, and each converts an input feature map into an output feature map. At least one of the layers is a depth map layer, the depth information image being ascertained as a function of a depth map layer. In the depth map layer, an input feature map of the depth map layer is convoluted with multiple scaling filters to obtain respective scaling maps, the multiple scaling maps are compared pixel by pixel to generate a respective output feature map in which each pixel corresponds to a corresponding pixel from a selected one of the scaling maps.