Abstract: A device and a computer-implemented method for a neural architecture search. A first set of values is provided for parameters that define at least one part of an architecture for an artificial neural network, wherein the part of the architecture encompasses a plurality of layers of the artificial neural network and/or a plurality of operations of the artificial neural network, wherein a first value of a function is determined for the first set of values for the parameters, said first value characterizing a property of a target system when the target system executes a task for the part of the artificial neural network that is defined by the first set of values for the parameters.

Abstract: A method for operating a calculation system including a neural network, in particular a convolutional neural network, the calculation system including a processing unit for the sequential calculation of the neural network and a memory external thereto for buffering intermediate results of the calculations in the processing unit, including: incrementally calculating data sections, which each represent a group of intermediate results, with the aid of a neural network; lossy compression of one or multiple of the data sections to obtain compressed intermediate results; and transmitting the compressed intermediate results to the external memory.

Abstract: A hardware architecture for an artificial neural network ANN. The ANN includes a consecutive series made up of an input layer, multiple processing layers, and an output layer. Each layer maps a set of input variables onto a set of output variables, and output variables of the input layer and of each processing layer are input variables of the particular layer that follows in the series. The hardware architecture includes a plurality of processing units. The implementation of each layer is split among at least two of the processing units, and at least one resettable switch-off device is provided via which at least one processing unit is selectively deactivatable, independently of the input variables supplied to it, in such a way that at least one further processing unit remains activated in all layers whose implementation is contributed to by this processing unit.

Abstract: A method for verifying a calculation of a neuron value of multiple neurons of a neural network, including: carrying out or triggering a calculation of neuron functions of the multiple neurons, in each case to obtain a neuron value, the neuron functions being determined by individual weightings for each neuron input; calculating a first comparison value as the sum of the neuron values of the multiple neurons; carrying out or triggering a control calculation with one or multiple control neuron functions and with all neuron inputs of the multiple neurons, to obtain a second comparison value as a function of the neuron inputs of the multiple neurons and of the sum of the weightings of the multiple neurons assigned to the respective neuron input; and recognizing an error as a function of the first comparison value and of the second comparison value.

Abstract: A system and method for providing classified digital recordings, for a system for automatic machine learning. A first digital recording is captured at a first point in time which includes an object situated at the first point in time at a first distance from the recording unit. A first classification of the object is determined using the data of the first digital recording. At a second point in time, a second digital recording is captured, which includes the object situated at the second point in time at a second distance from the recording unit. A second classification of the object is determined using the data of the second digital recording. A digital recording classified using a result of the second classification is provided, which includes at least a part of the first digital recording when a result of the first classification differs from the result of the second classification.

Abstract: A device, a memory medium, a computer program, and a computer-implemented method for validating a data-based model for classifying an object into a class for an object type or a function type for a driver assistance system of a vehicle. The classification is determined as a function of a digital signal using the data-based model. A reference classification for the object is determined as a function of the digital signal, using a reference model. It is checked, as a function of the classification and the reference classification, whether or not the classification of the data-based model for the object is correct, and the data-based model is validated or not validated, depending on whether or not the classification is correct. The classification and the reference classification are determined for a set of digital signals that are associated with different distances between the object and a reference point.

Abstract: A device and method for processing data, in particular unnormalized, multidimensional data, of a neural network, in particular a deep neural network, especially for detecting objects in an input image. The data includes at least one first classification value for a multitude of positions in the input image in each case, a classification value quantifying a presence of a class. The method includes the following steps: evaluating the data as a function of a threshold value, a first classification value for a respective position in the input image that lies either below or above the threshold value being discarded, and a first classification value for a respective position in the input image that lies either above or below the threshold value not being discarded.

Abstract: A hardware architecture for an artificial neural network ANN. The ANN includes a consecutive series made up of an input layer, multiple processing layers, and an output layer. Each layer maps a set of input variables onto a set of output variables, and output variables of the input layer and of each processing layer are input variables of the particular layer that follows in the series. The hardware architecture includes a plurality of processing units. The implementation of each layer is split among at least two of the processing units, and at least one resettable switch-off device is provided via which at least one processing unit is selectively deactivatable, independently of the input variables supplied to it, in such a way that at least one further processing unit remains activated in all layers whose implementation is contributed to by this processing unit.

Abstract: A method for operating a calculation system including a neural network, in particular a convolutional neural network, the calculation system including a processing unit for the sequential calculation of the neural network and a memory external thereto for buffering intermediate results of the calculations in the processing unit, including: incrementally calculating data sections, which each represent a group of intermediate results, with the aid of a neural network; lossy compression of one or multiple of the data sections to obtain compressed intermediate results; and transmitting the compressed intermediate results to the external memory.

Abstract: A method for verifying a calculation of a neuron value of multiple neurons of a neural network, including: carrying out or triggering a calculation of neuron functions of the multiple neurons, in each case to obtain a neuron value, the neuron functions being determined by individual weightings for each neuron input; calculating a first comparison value as the sum of the neuron values of the multiple neurons; carrying out or triggering a control calculation with one or multiple control neuron functions and with all neuron inputs of the multiple neurons, to obtain a second comparison value as a function of the neuron inputs of the multiple neurons and of the sum of the weightings of the multiple neurons assigned to the respective neuron input; and recognizing an error as a function of the first comparison value and of the second comparison value.