Abstract: A retrieval-augmented generative system is provided, including a user interface configured to receive a prompt from a user; a retrieval unit configured to retrieve documents relevant to the prompt; a concealment unit configured to identify at least one document among the retrieved documents including restricted information and to mark it being a confidential document; a large language model unit configured to input all retrieved documents including the at least one marked confidential document into a large language model and to output from the large language model a response containing restricted information and unrestricted information; and an output interface configured to provide the response including the restricted information in a concealed form to a user.

Abstract: A method for automatically quantifying a robustness of an object detection model applied for a controlling task and/or a monitoring task is provided, including—receiving the object detection model which is trained to output a predicted object in terms of a location in an image data and of an object class out of a set of object classes when the image data is input into the object detection model, —applying a set of robustness requirements to the object detection model, —deriving from each robustness requirement a cross Lipschitz-ness function, —determining a robustness value of the object detection model deviating from the un-perturbed image data of the image data, —comparing the determined robustness value with a predefined robustness threshold value, and—outputting a positive certification for applying the object detection model in the controlling task and/or the monitoring task if the robustness value is below the predefined robustness threshold value.

Abstract: An image analysis device (BA) is configured to recognize imaged objects. A plurality of training images (TPIC) assigned to an object type (OT) and an object sub-type (OST) are fed into a first neural network module (CNN) to detect image features. Training output data sets (FEA) of the first neural network module are fed into a second neural network module (MLP) to detect object types using the detected image features. For each object type: training images assigned to the object type (OT1, OT2) are fed into the trained first neural network module, the first neural network module training output data set (FEA1, FEA2) generated for the respective training image is assigned to the object sub-type (OST) of the respective training image, and by means of the aforementioned sub-type assignments, a sub-type detection module (BMLP1, BMLP2) is configured to detect object sub-types.

Abstract: The following relates to a computer-implemented method and system for transforming a trained artificial intelligence model into a trustworthy artificial intelligence model, by providing the trained artificial intelligence model via a user interface of a webservice platform, providing a validation data set, which is based on training data of the trained artificial intelligence model, generating generic samples by a computing component of the webservice platform based on the validation data set, and transforming the trained artificial intelligence model by optimizing a calibration based on the generic samples. The transformation of the AI model is performed by a computing component of the web service platform. The input, i.e. the trained artificial intelligence model as well as a validation data set, is provided to the computing component via a user interface of the web service platform. Such a user interface is implemented by any applicable frontend.

Abstract: A verification component for verifying an artificial intelligence, AI, model is provided, the verification component configured for receiving an input data set including the AI model to be verified, associated model data and application data; the verification component configured for determining at least one risk assessment score using at least one verification suite based on the input data set; the verification component configured for determining at least one Key Performance Indicator, KPI, by monitoring the performance of the AI model based on the input data set; the verification component configured for determining a validity of the AI model as at least one verification score based on the at least one risk assessment score and/or the at least one KPI; and the verification component configured for providing the at least one verification score and/or the verified AI model as output data set.

Abstract: Various embodiments of the teachings herein include a method for providing a setting for a given parameter to be adjusted. The method may include: providing a plurality n with n?2 of given input variables VARv with v=1, . . . , n to a prepared recommender system; processing the input with a modeling function to determine the recommended setting; and setting the given parameter to the recommended setting. Input variables VARv correspond to different variable types VARTv. For a particular variable type VARTv a plurality Tv of respective variables VARTv,t is available with t=1, . . . , Tv. For each variable type VARTv only one variable VARTv,t is provided as input variable VARv=VARTv,t. The modeling function is a function trained based on a Gaussian process with DCOM˜(0,Kcoreg+?2I) defined by a characterizing covariance matrix Kcoreg and a corresponding characterizing kernel kSEPcoreg.

Abstract: A computer-implemented method and system for transforming a trained artificial intelligence (AI) model into a trustworthy artificial intelligence model, wherein the trained AI model is provided via a user interface of a webservice platform, a validation data set based on training data of the trained artificial intelligence model is provided, generic samples are generated by a computing component of the webservice platform based on the validation data set, the trained artificial intelligence model is transformed by optimizing a calibration based on the generic samples, where the transformation of the artificial intelligence model is performed by a computing component of the web service platform, and the input, i.e. the trained artificial intelligence model and a validation data set, is provided therefor to the computing component via a user interface of the web service platform.

Abstract: A seat attachment system for a mass transit vehicle including a rail, a fastener and a seat interface. The rail, which is adapted to be secured to a chassis of the mass transit vehicle, has a longitudinal T-slot adapted to receive the fastener. The rail has two non-parallel sets of corrugations on its external face. The seat interface, which is adapted to be mounted to a seat frame, is also provided with two non-parallel sets of corrugations whose angle matches that of the sets of corrugations on the rail. The sets of corrugations are adapted to cooperate and interlock in pairs so as to respectively locate the seat interface, and thereby a seat to which it is attached, vertically and horizontally upon the fastener being tightened.

Abstract: The disclosed relates to a computer-implemented method of training a Neural Network as well as a corresponding computer program, computer-readable medium and data processing system. In addition to a categorical cross-entropy loss LCCE weights of the NN are updated based on predictive entropy loss LS and an adversarial calibration loss Ladv.

Abstract: The invention refers to a natural language processing system configured for receiving an input sequence ci of input words (v1, v2, . . . vN) representing a first sequence of words in a natural language of a first text and generating an output sequence of output words (, , . . . ) representing a second sequence of words in a natural language of a second text and modeled by a multinominal topic model, wherein the multinominal topic model is extended by an incorporation of language structures using a deep contextualized Long-Short-Term Memory model.

Abstract: A device for determining a spindle status of a spindle of a machine tool includes a detector for detecting sensor data of the spindle for a defined time window. A processing unit analyses the sensor data through artificial intelligence by calculating a defined feature of the sensor data for the defined time window and determining a spindle status from the sensor data. An output member outputs the determined spindle status.

Abstract: A computer-implemented method and a data processing apparatus provide and apply a trained probabilistic graphical model for verifying and/or improving the consistency of labels within the scope of medical image processing. Also provided are a computer-implemented method for verifying and/or improving the consistency of labels within the scope of medical imaging processing, a data processing apparatus embodied to verify and/or improve the consistency of labels within the scope of medical image processing, and a corresponding computer program product and a computer-readable medium.

Abstract: The following relates to a computer-implemented method and system for transforming a trained artificial intelligence model into a trustworthy artificial intelligence model, by providing the trained artificial intelligence model via a user interface of a webservice platform, providing a validation data set, which is based on training data of the trained artificial intelligence model, generating generic samples by a computing component of the webservice platform based on the validation data set, and transforming the trained artificial intelligence model by optimizing a calibration based on the generic samples. The transformation of the AI model is performed by a computing component of the web service platform. The input, i.e. the trained artificial intelligence model as well as a validation data set, is provided to the computing component via a user interface of the web service platform. Such a user interface is implemented by any applicable frontend.

Abstract: The aim of the invention is to configure an image analysis device (BA). This is achieved in that a plurality of training images (TPIC) assigned to an object type (OT) and an object sub-type (OST) are fed into a first neural network module (CNN) in Order to detect image features. Furthermore, training output data sets (FEA) of the first neural network module (CNN) are fed into a second neural network module (MLP) in Order to detect object types using image features. According to the invention, the first and second neural network module (CNN, MLP) are trained together such that training output data sets (OOT) of the second neural network module (MLP) at least approximately reproduce the object types (OT) assigned to the training images (TPIC).

Abstract: A seat attachment system for a mass transit vehicle including a rail, a fastener and a seat interface. The rail, which is adapted to be secured to a chassis of the mass transit vehicle, has a longitudinal T-slot adapted to receive the fastener. The rail has two non-parallel sets of corrugations on its external face. The seat interface, which is adapted to be mounted to a seat frame, is also provided with two non-parallel sets of corrugations whose angle matches that of the sets of corrugations on the rail. The sets of corrugations are adapted to cooperate and interlock in pairs so as to respectively locate the seat interface, and thereby a seat to which it is attached, vertically and horizontally upon the fastener being tightened.

Abstract: Provided is a computer-implemented method for post-processing output data of a classifier, including the steps: a. providing a validation data set with a plurality of labelled sample pairs, wherein each labelled sample pair comprises a model input and a corresponding model output; b. providing a plurality of perturbation levels; c. generating at least one perturbated sample pair for each labelled sample pair of the plurality of labelled sample pairs using a perturbation method based on the respective labelled sample pair and at least one perturbation level of the plurality of perturbation levels; d. determining a post-processing model based on the plurality of perturbated sample pairs; e. applying the determined post-processing model on testing data to post-process the output data of the classifier; and f. providing the post-processed output data of the classifier. Also provided is a corresponding technical unit and computer program product.

Abstract: The present invention concerns a text analysis system, the text analysis system being adapted for utilizing a topic model to provide a document representation. The topic model is based on learning performed on a text corpus utilizing hidden layer representations associated to words of the text corpus, wherein each hidden layer representation pertains to a specific word of the text corpus and is based on a word environment including words occurring before and after the specific word in a text of the text corpus.

Abstract: The invention refers to a natural language processing system configured for receiving an input sequence ci of input words representing a first sequence of words in a natural language of a first text and generating an output sequence of output words representing a second sequence of words in a natural language of a second text and modeled by a multinominal topic model, wherein the multinominal topic model is extended by an incorporation of full contextual information around each word vi, wherein both preceding words v<i and following words v>i around each word vi are captured by using a bi-directional language modelling and a feed-forward fashion, wherein position dependent forward hidden layers {right arrow over (h)}i and backward hidden layers i for each word vi are computed.

Abstract: A control device of an automation system, which is configured to control a plant, such as a production plant, including using an AI system, is provided. In an application of the control device, the device monitors the production with regard to the quality of the objects produced, for example, with regard to the presence of fault cases. The AI system is trained in advance based on a plurality of known states of the objects, so that the AI system may be trained for the occurrence of new, previously unknown states, where only a small number of example cases are required.

Abstract: The disclosed relates to a computer-implemented method of training a Neural Network as well as a corresponding computer program, computer-readable medium and data processing system. In addition to a categorical cross-entropy loss LCCE weights of the NN are updated based on predictive entropy loss LS and an adversarial calibration loss Ladv.