Abstract: A method for training a neural network for determining a task output with respect to a given task. The method includes: providing unlabeled and/or labelled encoder training records of measurement data; training the encoder network to map encoder training records to representations towards the goal that these representations, and/or or one or more work products derived from the representations, fulfil a self-consistency condition or correspond to ground truth; providing task training records that are labelled with ground truth; and training the association network and the task head networks towards the goal that, when a task training record is mapped to a representation using the encoder network, and the representation is mapped to a task output by the combination of the association network and the task head networks, the so-obtained task output corresponds to the ground truth with which the training record is labelled, as measured by a task loss function.

Abstract: A prediction device is described for predicting a location of a pedestrian moving in an environment. The prediction device may have a memory configured to store a probability distribution for multiple latent variables indicating one or more states of the one or more pedestrians. The prediction device may be configured to predict a position of a pedestrian for which no position information is currently available from the probability distribution of the multiple latent variables.

Abstract: An image classifier for classifying an input image x with respect to combinations of an object value o and an attribute value. The image classifier includes an encoder network that is configured to map the input image to a representation comprising multiple independent components; an object classification head network configured to map representation components of the input image to one or more object values; an attribute classification head network configured to map representation components of the input image to one or more attribute values; and an association unit configured to provide, to each classification head network, a linear combination of those representation components of the input image x that are relevant for the classification task of the respective classification head network. A method for training the image classifier is also provided.

Abstract: A method for generating, from an input image, an output image that a given image classifier classifies into a target class chosen from multiple available classes of a given classification. The method includes mapping, using a trained encoder network, the input image to a lower dimensional representation in a latent space; drawing a noise sample from a given distribution; and mapping, using a trained generator network, the noise sample to an output image, wherein this mapping is conditioned both on the target class and on the representation.

Abstract: Computer-implemented method for determining an output signal based on an input signal and by means of a neural network. The neural network determines the output signal based on a layer output determined by a first layer of the neural network. The layer output is determined based on scaling a layer input of the first layer and shifting the scaled layer input, wherein the scaling and shifting is based on a plurality of auxiliary inputs provided to the first layer.

Abstract: A computer-implemented prediction method of making time-series predictions for controlling and/or monitoring a computer-controlled system, such as a semi-autonomous vehicle. The method uses a time series of one or more observed states. A state comprises values of measurable quantities of multiple interacting objects. Based on the observed states, values of time-invariant latent features for the multiple objects are determined, for example, according to an encoder model. A decoder model is then used to predict at least one next state. This involves applying a trained graph model to obtain a first prediction contribution based on an object's interactions with other objects, and applying a trained function to obtain a second prediction contribution based just on information about the object itself. Based on the predicted next state, output data is generated for use in controlling and/or monitoring the computer-controlled system.

Abstract: A prediction device is described for predicting a location of a pedestrian moving in an environment. The prediction device may have a memory configured to store a probability distribution for multiple latent variables indicating one or more states of the one or more pedestrians. The prediction device may be configured to predict a position of a pedestrian for which no position information is currently available from the probability distribution of the multiple latent variables.