Robert Boschgmbh

Maja Rita Rudolph

Chen Qiu

Samuel Vasconcelos Araujo

Michael Jiptner

Dennis Bura

A computer-implemented method for training a deep state space model using machine learning. The deep state space model includes a generative model and a multi-modal inference model. The generative model includes a transition model, and an emission model. The method includes: a) receiving a training data set comprising a sequence of observation vectors. For a plurality of observation vectors, the method iterates between b), c), and d) in sequence: b) inferring, using the multi-modal inference model, a current latent state of the generative model; c) constructing, using the multi-modal inference model, a posterior approximation of the current latent state as a mixture density network. For a plurality of observation vectors comprised in the sequence of observation vectors, d) decoding, using the emission model, the plurality of approximated latent state vectors to provide a plurality of synthetic observations; and e) outputting the trained deep state space model.

Forecasting with deep state space models

A method is disclosed for operating a technical apparatus with an electronic converter controlled a control signal. A control signal profile is provided with which the electronic converter is to be operated. A predicted control signal profile is predicted based on the provided control signal profile. The predicted control signal profile is a predicted future profile of the control signal. A modified control signal profile of is obtained by modifying the provided control signal profile using a trainable, data-based control signal model. The control signal model is trained to determine the modified control signal profile based on the provided control signal profile and the predicted control signal profile. The electronic converter is operated using the modified control signal profile.

Growing community of inventors

Tuebingen, Germany

Maja Rita Rudolph