Robert Boschgmbh

Volker Fischer

Jan Hendrik Metzen

Chaithanya Kumar Mummadi

Max Welling

Anna Khoreva

Yorck Von Collani

Andres Mauricio Munoz Delgado

Clemens Guenther

Piyapat Saranrittichai

Michael Herman

Thomas Pfeil

Claudia Blaiotta

Nicole Ying Finnie

Joerg Wagner

Zeynep Akata

Victor Garcia Satorras

Irene Suessemilch

Prateek Katiyar

Lukas Hoyer

Christoph Rohrer

Anurag Pandey

Ramona Roesch

Stephanie Linder

A computer-implemented method for training a classifier. The classifier is configured to determine an output signal characterizing a classification of an input signal. The training of the classifier includes: determining a first training input signal; determining a first latent representation comprising a plurality of factors based on the first training input signal by means of an invertible factorization model, wherein the invertible factorization model, determining a second latent representation by adapting at least one factor of the first latent representation; determining a second training input signal based on the second latent representation by means of the invertible factorization model; and training the classifier based on the second training input signal.

Device and method for training a classifier using an invertible factorization model

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.

Training neural networks with a lesser requirement for labelled training data

A system and method, in particular computer implemented method for determining a perturbation for attacking and/or validating an association tracker. The method includes providing digital image data that includes an object, determining with the digital image data a first feature that characterizes the object, providing in particular from a storage a second feature that characterizes a tracked object, determining the perturbation depending on a measure of a similarity between the first feature and the second feature.

System and method, in particular computer implemented method for determining a perturbation for attacking and/or validating an object tracker

Systems and computer-implemented methods for training a machine learnable model and for using the machine learned model for inference, both of which using only limited memory resources. During training and inference, the machine learnable model uses previous state information. A state memory is provided which efficiently stores this previous state information. Instead of storing each previous state individually and integrally, for each element of the internal state, a value is stored in the state memory which is indicative of a most recent occurrence of an element of the internal state of the machine learnable model holding or transitioning to a particular binary state value. The states of the machine learnable model are representable as binary values and when states infrequently hold or transition to a particular binary state value.

Efficient temporal memory for sparse binary sequences

A method and system for representing an environment of a first mobile platform. The method includes: capturing features of the environment by discrete time sequences of sensor-data from at least two sensors and respective time markers; determining distances of the first mobile platform to the features of the environment; estimating semantic information of the features of the environment; transforming the semantic information of the features of the environment into a moving spatial reference system, wherein a position of the first mobile platform is at a constant site, using the respective determined distances and respective time markers; creating an input tensor using sequences of the transformed semantic information of the features of the environment, corresponding to the sequences of the sensor data of the at least two sensors; generating an output tensor that represents the environment using a deep neural network at a requested point in time and the input tensor.

Method for representing an environment of a mobile platform

A device for operating a machine learning system. The machine learning system is assigned a predefinable rollout, which characterizes a sequence in which each of the layers ascertains an intermediate variable. When assigning the rollout, each connection or each layer is assigned a control variable, which characterizes whether the intermediate variable of each of the subsequent connected layers is ascertained according to the sequence or regardless of the sequence. A calculation of an output variable of the machine learning system as a function of an input variable of the machine learning system is controlled as a function of the predefinable rollout. Also described is a method for operating the machine learning system.

Device, configured to operate a machine learning system based on predefinable rollout

A system and computer-implemented method are provided for enabling control of a physical system based on a state of the physical system which is inferred from sensor data. The system and method may iteratively infer the state by, in an iteration, obtaining an initial inference of the state using a mathematical model representing a prior knowledge-based modelling of the state, and by applying a learned model to the initial inference of the state and the sensor measurement, wherein the learned model has been learned to minimize an error between initial inferences provided by the mathematical model and a ground truth and to provide a correction value as output for correcting the initial inference of the state of the mathematical model. Output data may be provided to an output device to enable control of the physical system based on the inferred state.

Control of a physical system based on inferred state

A method for efficiently ascertaining output signals of a sequence of output signals with the aid of a sequence of layers of a machine learning system, in particular a neural network, from a sequence of input signals. The neural network is supplied in succession with the input signals of the sequence of input signals in a sequence of discrete time increments. At the discrete time increments, signals present in the network are in each case further propagated through a layer of the sequence of layers.

Method and device for efficiently ascertaining output signals of a machine learning system

A method is described for measuring the vulnerability of an AI module to spoofing attempts, including the classification and/or regression onto which the AI module maps the update data set is ascertained as an unperturbed result for a predefined data set in the input space E; at least one perturbation S having a dimensionality d&#x3c;D is applied to the predefined data set so that at least one perturbed data set results in the input space E; the classification and/or regression onto which the AI module maps the perturbed data set is ascertained as the perturbed result; the deviation of the perturbed result from the unperturbed result is ascertained using predefined metrics; in response to the deviation satisfying a predefined criterion, it is determined that the AI module with regard to the predefined data set is vulnerable to spoofing attempts having a dimensionality d.

Measuring the vulnerability of AI modules to spoofing attempts

A method for generating a universal data signal interference for generating a manipulated data signal for deceiving a first machine learning system, which is configured to ascertain a semantic segmentation of a received one-dimensional or multidimensional data signal, The method includes a) ascertaining a training data set that includes pairs of data signals and associated desired semantic segmentations, b) generating the data signal interference, as a function of the data signals of the training data set, of the associated desired semantic segmentation, as well as of estimated semantic segmentations of the data signals acted upon by the data signal interference.

Method and device for improving the robustness against 'adversarial examples'

A method for generating a manipulated data signal for misleading a first machine learning system, which is designed to ascertain a semantic segmentation of a received one-dimensional or multi-dimensional data signal, the method having the following steps: a) ascertaining a desired semantic segmentation of the manipulated data signal; and b) generating the manipulated signal as a function of the received data signal and the ascertained desired semantic segmentation as well as an estimated semantic segmentation of the manipulated data signal.

Method and device for improving the robustness with respect to 'adversarial examples'

A method for detecting an object with the aid of a system, the system having a plurality of modules connected in series one after the other, at least one connection between a predefinable module and its immediately following module being implemented in each case with the aid of a filter and storage module connected in series, the first module of the modules connected in series being connected to an acquisition unit, and the last module of the modules connected in series being connected to a detection module. The method includes temporal filtering.

Method, device, and computer program for detecting an object

A projection unit for a self-directing mobile platform, in particular for a freely moving transport robot and/or for one or more freely moving transport devices of a transport robot, is characterized in that the projection unit is adapted for signal transmission for projecting the movement path of the mobile platform, wherein the projection takes place within the spatial vicinity of the mobile platform.

Growing community of inventors

Leonberg, Germany

Volker Fischer