Method for monitoring logical consistency in a machine learning model and associated monitoring device
AssigneeAUMOVIO Germany GmbH
InventorsGesina Schwalbe, Christian Wirth
Life of this patent
Estimating the term…
Abstract
A computer-implemented method monitors the logical consistency of an artificial neural network. Activation data of the artificial neural network, which are produced from input data, is initially read in. The activation data is transferred to at least one trained concept model which is trained to recognize and, if applicable, localize a partial feature of the features contained in the input data and to output a calibrated partial feature mask. The final output data is linked to the partial feature truth values by a fuzzy logic unit to produce a continual logical consistency truth value. The logical consistency truth value is evaluated by an evaluation unit.
Claims15
A computer-implemented method for monitoring a logical consistency of an artificial neural network which is configured for a classification, classification and localization, object detection, or segmentation of features which are contained in input data, and for outputting final output data which are indicative of the existence and, if applicable, a position of the features in the input data, the method comprising:
- (a) reading in activation data of the artificial neural network, which are produced from the input data, by an input interface;
- (b) transferring the activation data read in (a) to at least one trained concept model which is trained to recognize and, if applicable, localize a partial feature of the features contained in the input data, and to output a partial feature mask, wherein the partial feature mask contains at least one partial feature truth value which is indicative of whether and, if applicable, where the partial feature is contained in the input data;
- (c) linking the final output data to the partial feature truth value by a fuzzy logic unit which determines at least one continual logical consistency truth value therefrom;
- (d) evaluating the at least one continual logical consistency truth value obtained in (c) by an evaluation unit, wherein, if the at least one continual logical consistency truth value reaches or falls short of a predefined threshold, the evaluation unit ascertains a logical inconsistency of the final output data in an inconsistency region, wherein the evaluation unit ascertains a logical consistency if the at least one continual logical consistency truth value does not fall short of the predefined threshold;
- and
- (e) in the event that no logical consistency of the final output data with the input data was ascertained in (d), activating additional sensors or controlling a vehicle component.
A non-transitory computer-readable storage medium comprising commands which, when executed by a computer;
- (a) read in activation data of an artificial neural network via an input interface, the artificial neural network being configured for a classification, classification and localization, object detection, or segmentation of features which are contained in input data, and for outputting final output data which are indicative of the existence and, if applicable, a position of the features in the input data, the activation data being produced from the input data;
- (b) transfer the activation data read in (a) to at least one trained concept model which is trained to recognize and, if applicable, localize a partial feature of the features contained in the input data, and to output a partial feature mask, wherein the partial feature mask contains at least one partial feature truth value which is indicative of whether and, if applicable, where the partial feature is contained in the input data;
- (c) link the final output data to the partial feature truth value by a fuzzy logic unit which determines at least one continual logical consistency truth value therefrom;
- (d) evaluate the at least one continual logical consistency truth value obtained in (c) by an evaluation unit, wherein, if the at least one continual logical consistency truth value reaches or falls short of a predefined threshold, the evaluation unit ascertains a logical inconsistency of the final output data in an inconsistency region, wherein the evaluation unit ascertains a logical consistency if the at least one continual logical consistency truth value does not fall short of the predefined threshold;
- and
- (e) in the event that no logical consistency of the final output data with the input data was ascertained in (d), activating additional sensors or controlling a vehicle component.
Dependencies are inferred from the claim text.