Siemens Aktiengesellschaft

Siemens Healthcare Diagnostics Gmbh

Florian Büttner

Pankaj Gupta

Markus Michael Geipel

Felix Buggenthin

Christoph Tietz

Gaby Marquardt

Daniela Seidel

Christian Tomani

Yatin Chaudhary

Silvio Becher

Matthias Kereit

Igor Kogan

Felix Butz

Klaus Böhme

Philipp Siegel

Werner Vom Eyser

Georg Domaschke

Michael Helbig

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 (OT, OT) are fed into the trained first neural network module, the first neural network module training output data set (FEA, FEA) 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 (BMLP, BMLP) is configured to detect object sub-types.

Method for configuring an image evaluation device and also image evaluation method and image evaluation device

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.

Transforming a trained artificial intelligence model into a trustworthy artificial intelligence model

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 Lweights of the NN are updated based on predictive entropy loss Land an adversarial calibration loss L.

Trustworthy predictions using deep neural networks based on adversarial calibration

The invention refers to a natural language processing system configured for receiving an input sequence cof input words (v, v, . . . v) 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.

System and method for natural language processing with a multinominal topic model

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.

Device and method for determining the status of a spindle of a machine tool

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.

Verifying and/or improving the consistency of labels within the scope of medical image processing

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.

Automatized text analysis

The invention refers to a natural language processing system configured for receiving an input sequence cof 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 v, wherein both preceding words vand following words varound each word vare captured by using a bi-directional language modelling and a feed-forward fashion, wherein position dependent forward hidden layers {right arrow over (h)}and backward hidden layersfor each word vare computed.

System and method for natural language processing

Provided is an in-field apparatus and method for automatic localization of a fault having occurred at power transmission lines of a power supply system, the in-field apparatus includes a preprocessing unit configured to process measured voltage and/or current raw time series data of the power transmission lines to provide a normalized raw data and/or feature representation of the measured raw time series data, and an artificial intelligence module configured to predict an optimal evaluation time used for evaluation of the measured voltage and/or current raw time series data to localize the fault based on the normalized raw data and/or feature representation.

Growing community of inventors

Munich, Germany

Florian Büttner