Abstract: A machine learning system, including at least one temporal filter. An input variable, encompassing a chronological sequence of images, is processed with the aid of the machine learning system, using the filter. The machine learning system is configured to use the filter on a sequence of pixels, which are all situated at identical coordinates of the images, or at identical coordinates of intermediate results. Filter coefficients of the filter are quantized. A method, a computer program, and a device for creating the machine learning system are also described.

Abstract: A method for generating a simplified computer-implemented neural network. The method includes: receiving a predefined neural network, which includes a plurality of neural network structures and is described by weights, each neural network structure being assigned a pruning vector which describes a change in weights as a result of the pruning of the respective neural network; calculating a product of a matrix including a structure vector, the matrix including partial second order derivations of a loss function with respect to the plurality of weights; determining changes in the loss function with respect to the predefined neural network, each change occurring as a result of a pruning of a corresponding neural network structure of the two or more neural network structures to be pruned; and pruning at least one neural network structure based on the determined two or more changes in the loss function to generate the simplified neural network.

Abstract: A method for operating an artificial neural network (ANN), which processes inputs in a sequence of layers, to give outputs. In the method: within the ANN, at least one iterative block comprising one or more layers is defined and is to be executed multiple times; a number J of iterations is defined; an input of the iterative block is mapped onto an output by the iterative block; the output is supplied to the iterative block again as an input and is mapped onto a new output; once the iterative block has been executed J times, the output delivered by the iterative block is supplied, as an input, to the layer of the ANN succeeding the iterative block or is provided as the output of the ANN. A portion of the parameters that characterize the behavior of the layers in the iterative block are changed between the iterations.

Abstract: A computer-implemented method for training a classifier. The classifier is configured to determine an output signal characterizing a classification of an input signal. The training of the classifier includes: determining a first training input signal; determining a first latent representation comprising a plurality of factors based on the first training input signal by means of an invertible factorization model, wherein the invertible factorization model, determining a second latent representation by adapting at least one factor of the first latent representation; determining a second training input signal based on the second latent representation by means of the invertible factorization model; and training the classifier based on the second training input signal.

Abstract: A computer-implemented method for determining an output signal for an input signal using a classifier. The output signal characterizes a classification of the input signal. The method includes: determining a latent representation based on the input signal using an invertible factorization model comprised in the classifier, the latent representation comprises a plurality of factors; determining the output signal based on the latent representation using an internal classifier comprised in the classifier.

Abstract: A method which processes inputs in a sequence of layers to form outputs. Within an artificial neural network (ANN), at least one iterative block including one or more layer(s) is established, which is to be implemented multiple times. A number J of iterations is established, for which this iterative block is at most to be implemented. An input of the iterative block is mapped by the iterative block onto an output. This output is again fed to the iterative block as input and again mapped by the iterative block onto a new output. Once the iterative block has been implemented J-times, the output supplied by the iterative block is fed as the input to a following layer or is provided as output of the ANN. A portion of the parameters, which characterize the behavior of the layers in the iterative block, is changed during the switch between the iterations.

Abstract: A computer-implemented method for training a classifier is disclosed. The classifier is designed to determine an output (y) for an input data point (x). The output (y) characterizes a classification of the input data point (x). The classifier comprises a multiplicity of weights on the basis of which the output (y) is determined. At least one weight of the multiplicity of weights is quantized to a predefined first number of first values. Each two consecutive first values differ by a distance value. The distance value is also adjusted for training and the multiplicity of weights is not adjusted.

Abstract: A method for ascertaining a physical property of an object. The method includes detecting, for each input point in time of a sequence of input points in time, sensor data including information about a physical object, using an event-based sensor; for each subsequence of a breakdown of the sequence of input points in time into multiple subsequences including: feeding the sensor data detected for the input points in time of the subsequence to a pulsed neural network which generates a first processing result of the subsequence; feeding the processing result of the subsequence to a non-pulsed neural network; and processing the processing result of the subsequence by non-pulsed neurons of one or multiple first layer(s) of the non-pulsed neural network for generating a second processing result of the subsequence; and feeding the second processing results of the multiple subsequences to one or multiple second layer(s) of the non-pulsed neural network.

Abstract: A method for operating a deep neural network having at least one skip connection. The method includes: selecting a first path through the deep neural network along the specifiable sequence, using the skip connection; propagating an input variable along the first path; checking whether the output variable corresponds to a specifiable criterion, such that if the specifiable criterion is not met a further path through the deep neural network is selected that is longer by at least one layer than the first path, and the input variable is thereupon propagated along the second path with reuse of the intermediate results of the first path. A computer program, a device for carrying out the method, and a machine-readable storage element on which the computer program is stored, are also described.

Abstract: A computer-implemented classifier for ascertaining an output signal as a function of an input signal supplied to the classifier. The classifier is designed to select one type of quantization from a plurality of possible types of quantization, and to carry out the ascertainment of the output signal as a function of the selected type of quantization.

Abstract: A machine learning system, in particular a deep neural network. The machine learning system includes a plurality of layers that are connected to one another. The layers each ascertain an output variable as a function of an input variable and at least one parameter that is stored in a memory. The parameters of those layers that are connected to a further, in particular preceding, layer are each stored in the memory using a higher resolution than the parameters of those layers that are connected to a plurality of further, in particular preceding, layers. In addition, A method, a computer program, and a device for creating the machine learning system, are described.

Abstract: A method for creating a pulsed neural network (Spiking Neural Network). The method begins with an assignment of a predefinable control pattern (rollout pattern) to a deep neural network. This is followed by a training of the deep neural network using the control pattern. This is followed by a conversion of the deep neural network into the pulsed neural network, the connections of the pulsed neural network being assigned a delay, in each case as a function of the control pattern. A computer program, a device for carrying out the method, and to a machine-readable memory element are also described.

Abstract: A method for compressing a deep neural network. The deep neural network includes a multitude of layers, which are each connected on the input side according to a predefinable sequence to their directly preceding layer of the sequence. The method includes adding a skip connection. Thereafter, a reduction of a resolution of the parameters of the layers follows. A computer program as well as to a device for carrying out the method are also described.

Abstract: A machine learning system, including at least one temporal filter. An input variable, encompassing a chronological sequence of images, is processed with the aid of the machine learning system, using the filter. The machine learning system is configured to use the filter on a sequence of pixels, which are all situated at identical coordinates of the images, or at identical coordinates of intermediate results. Filter coefficients of the filter are quantized. A method, a computer program, and a device for creating the machine learning system are also described.