Siemens Aktiengesellschaft

Drimco Gmbh

Siemens Energy Global Gmbh & Co. Kg

Thomas Runkler

Per Egedal

Steffen Udluft

Volkmar Sterzing

Manfred Baldauf

Marc Christian Weber

Mikhail Roshchin

Clemens Otte

Pankaj Gupta

Markus Michael Geipel

Alexander Hentschel

Sebastian Mittelstädt

Ralph Grothmann

Daniel Hein

Arno Arzberger

Johannes Kehrer

Frank Steinbacher

Gulnar Mehdi

Klaus Arthur Schmid

Klaus-Peter Hitzel

Michael Schnurbusch

Phillip Swazinna

Khushbu Saxena

Jonas Witt

Jürgen Baus

Michael Rock

Hiba Arnout

Sebastian-Philipp Brandt

Johanna Bronner

Gunnar Stoelben

Siegmund DÜLL

Various embodiments of the teachings herein include a computer-implemented method of fine-tuning Natural Language Processing (NLP) models. Some examples include: providing a training data set including a multitude of training text documents; providing a NLP model including a Neural Network (NN) based Topic Model (TM) having scalable TM parameters and a parallel large-scale pre-trained Language Model (LM) having scalable LM parameters; and fine-tuning the NLP model by jointly training the NN-based TM and the parallel large-scale pre-trained LM using a projected vector comprising a combination and projection of a document topic proportion generated by the NN-based TM based on the scalable TM parameters from an input training text document of the multitude of training text documents, and of a contextualized document representation generated by the large-scale pre-trained LM based on the scalable LM parameters from the same input training text document.

Decarbonizing BERT with topics for efficient document classification

To configure a control agent, predefined training data are read in, which specify state datasets, action datasets and resulting performance values of the technical system. Using the training data, a data-based dynamic model is trained to reproduce a resulting performance value using a state dataset and an action dataset. An action evaluation process is also trained to reproduce the action dataset using a state dataset and an action dataset after an information reduction has been carried out, wherein a reproduction error is determined. To train the control agent, training data are supplied, the trained action evaluation process and the control agent. Performance values output by the trained dynamic model are fed into a predefined performance function. Reproduction errors are fed as performance-reducing influencing variables into the performance function. The control agent is trained to output an action dataset optimising the performance function on the basis of a state dataset.

Method for configuring a control agent for a technical system, and control device

An evaluation framework for a generated dataset of a data generation algorithm such as a generative adversarial network is provided. The generated dataset includes a plurality of iterations of multiple instances of generated time series of data points. The evaluation framework provides multiple views. A first view includes at least one distance measure. The at least one distance measure is between the multiple instances of the generated time series and multiple instances of a reference time series, as a function of the plurality of iterations.

Evaluation framework for time series data

Growing community of inventors

Munich, Germany

Thomas Runkler