Abstract: A method for lossy video encoding, transmission and decoding, the method comprising the steps of: receiving an input video at a first computer system; encoding an input frame of the input video to produce a latent representation; producing a quantized latent; producing a hyper-latent representation; producing a quantized hyper-latent; entropy encoding the quantized latent; transmitting the entropy encoded quantized latent and the quantized hyper-latent to a second computer system; decoding the quantized hyper-latent to produce a set of context variables, wherein the set of context variables comprise a temporal context variable; entropy decoding the entropy encoded quantized latent using the set of context variables to obtain an output quantized latent; and decoding the output quantized latent to produce an output frame, wherein the output frame is an approximation of the input frame.

Abstract: Apparatus and computer-implemented method, including: presetting data points which include pairs of mutually assigned input and output of a Gaussian process; determining a positive semi-definite kernel matrix from inputs predetermined by the data points; determining an inverse of the kernel matrix depending on an estimation for an inverse of a 1-Lipschitz mapping of the kernel matrix; presetting an input for the Gaussian process; determining a prediction for an expected value of the Gaussian process, and/or a prediction for a variance of the Gaussian process; determining a probable output variable of a sensor and/or a control variable for a machine depending on at least one of the predictions.

Abstract: A computer-implemented method for training a machine learning system for generating driving profiles and/or driving routes of a vehicle including: a generator obtains first random vectors and generates first driving routes and associated first driving profiles related to the first random vectors, driving routes and respectively associated driving profiles recorded in driving mode are stored in a data base, second driving routes and respectively associated second driving profiles recorded in driving mode are selected from the database, a discriminator obtains first pairs made up of first generated driving routes and respectively associated first generated driving profiles and second pairs made up of second driving routes and respectively associated second driving profiles recorded in driving mode, the discriminator calculates outputs that characterize each pair, and a target function is optimized as a function of the outputs of the discriminator.

Abstract: A computer-implemented method for training a machine learning system to generate driving profiles of a vehicle. The method includes first travel routes are selected from a first database having travel routes, a generator of the machine learning system receives the first travel routes and generates first driving profiles for each of the first travel routes, travel routes and associated driving profiles determined during vehicle operation are stored in a second database, second travel routes and respective associated second driving profiles determined during vehicle operation are selected from the second database, a discriminator of the machine learning system receives pairs made up of one of the first travel routes with the respective associated first generated driving profile and pairs made up of second travel routes with the respective associated second driving profile determined during vehicle operation, as input variables.

Abstract: To simulate automotive systems, a large number of synthetic data points characterising an aspect of the performance of a target automotive system are generator. In this way, for example, various future scenarios can be simulated and statistically evaluated. A computer-implemented method is provided for training a generative machine learning model, a computer-implemented method for generating synthetic data series using a generative machine learning model, and an associated apparatus. An associated computer program element and computer readable medium are also described.

Abstract: Feature attribution may be captured as part of a machine learning pipeline. A training job may include a request to determine feature attribution as part of a machine learning pipeline that trains a machine learning model from a training data set. A reference data set for determining the feature attribution of the machine learning model may be identified. The feature attribution may be determined based on the reference data set. The feature attribution of the trained machine learning model may be stored.

Abstract: Bias metrics may be captured at different stages for training a machine learning model. A training job may specify bias metrics to capture at multiple different stages of a machine learning pipeline for a feature of a training data set used to train a machine learning model. The training job may be executed and the bias metrics determined at the stages as specified in the training job. The bias metrics for the different stages may be stored.

Abstract: Bias metrics and feature attribution may be monitored for a machine learning model. A request to enable monitoring for bias metrics or feature attribution may be received. Monitoring may be enabled to evaluate respective performance of inferences of a machine learning model according to the enabled bias metrics or feature attribution. If a divergence from reference data is detected, then a notification indicating the divergence may be sent.

Abstract: Views may be generated for bias metrics or feature attribution captured in machine learning pipelines. A request to create a view of bias metrics or feature attribution may be received. The bias metrics or feature attribution may have been determined in a machine learning pipeline as part of executing a training job that specified the bias metrics or the feature attribution. A development application may access a data store that stores the bias metrics or the feature attribution determined in the machine learning pipeline. A view based on the bias metrics or feature attribution may be generated and provided.

Abstract: A method for determining a state of a transmission for a vehicle, including providing an input for a first generative model depending on a route information, a vehicle speed, a probabilistic variable, and an output of a second physical model, and determining an output of the first model characterizing the state in response to the input for the first model. The first model comprises a first layer trained to map input to an intermediate state. The first model comprises a second layer trained to map the intermediate state to the state depending on the output of the second model. The method includes providing an input for the second physical model depending on at least one vehicle state and/or the route information, and determining an output of the second model in response to the input for the second model. The output of the second model characterizes limit(s) for the intermediate state.

Abstract: A machine learning system and method of operating a machine learning system for determining a time series, comprising providing an input for a first in particular generative model depending on a probabilistic variable, determining an output of the first model in response to the input for the first model, the output of the first model characterizing the time series. The first model comprises a first layer that is trained to map input for the first model determined depending on the probabilistic variable to output characterizing intermediate data, and a second layer that is trained to map the intermediate data to the time series depending on an output of a third layer of the first model. The output of the third layer characterizes a physical constraint to a machine state. Values of the time series or of the intermediate data are constrained by the output of the third layer.

Abstract: A device, a machine learning system and a method for determining a velocity of a vehicle. The method includes providing an input for a first generative model depending on a route information, a probabilistic variable, including noise, and an output of a second physical model, determining an output of the first model in response to the input for the first model. The output of the first model characterizes the velocity. The first model comprises a first component that is trained to map input for the first model determined depending on the route information and the probabilistic variable to intermediate output for the velocity of the vehicle. The first model comprises a second component that is trained to map the intermediate output to the velocity depending on the output of the second model. The output of the second model characterizes a physical constraint for the velocity or for the intermediate output.

Abstract: A system for processing a model. The model provides a model output given an input instance. The model has been trained on a training dataset by iteratively optimizing an objective function including losses according to a loss function for training instances of the training dataset. Upon receiving a removal request message identifying one or more undesired training instances of the training dataset, the model is made independent from the one or more undesired training instances. To this end, the one or more undesired training instances are removed from the training dataset to obtain a remainder dataset, and an adapted model is determined for the remainder dataset. The parameters of the adapted model are first initialized based on the set of parameters of the trained model, and then iteratively adapted by optimizing the objective function with respect to the remainder dataset.

Abstract: A system for processing a classifier. The classifier is a Naïve Bayes-type classifier classifying an input instance into multiple classes based on multiple continuous probability distributions of respective features of the input instance and based on prior probabilities of the multiple classes. Upon receiving a removal request message identifying one or more undesired training instances, the classifier is made independent from one or more undesired training instances. To this end, for a continuous probability distribution of a feature, adapted parameters of the probability distribution are computed based on current parameters of the probability distribution and the one or more undesired training instances. Further, an adapted prior probability of a class is computed based on a current prior probability of the class and the one or more undesired training instances.

Abstract: A device, system, and method select a frequency band during an attenuation activity state. The method is performed at a device that is configured to establish a network connection to a network having a first priority of available frequency bands set by the network. The method includes identifying an attenuation activity state. The method includes generating a second priority of the available frequency bands based on the attenuation activity state. The method includes selecting one of the available frequency bands based on the second priority to establish the network connection.

Abstract: A computer-implemented method for training a machine learning system for generating driving profiles and/or driving routes of a vehicle including: a generator obtains first random vectors and generates first driving routes and associated first driving profiles related to the first random vectors, driving routes and respectively associated driving profiles recorded in driving mode are stored in a data base, second driving routes and respectively associated second driving profiles recorded in driving mode are selected from the database, a discriminator obtains first pairs made up of first generated driving routes and respectively associated first generated driving profiles and second pairs made up of second driving routes and respectively associated second driving profiles recorded in driving mode, the discriminator calculates outputs that characterize each pair, and a target function is optimized as a function of the outputs of the discriminator.

Abstract: A computer-implemented method for training a machine learning system to generate driving profiles of a vehicle. The method includes first travel routes are selected from a first database having travel routes, a generator of the machine learning system receives the first travel routes and generates first driving profiles for each of the first travel routes, travel routes and associated driving profiles determined during vehicle operation are stored in a second database, second travel routes and respective associated second driving profiles determined during vehicle operation are selected from the second database, a discriminator of the machine learning system receives pairs made up of one of the first travel routes with the respective associated first generated driving profile and pairs made up of second travel routes with the respective associated second driving profile determined during vehicle operation, as input variables.

Abstract: A memory circuit according to some examples may include a clock delay circuit that use a polarity of a write enable signal to determine an operation (i.e. write or read) on the memory that provides the desired clock latency to the memory. The clock delay circuit may have a low skew portion and a high skew portion. The selection of the high skew portion or low skew portion may depend on the status of the write enable line, such as a polarity or logical value.

Abstract: A memory circuit according to some examples may include a clock delay circuit that use a polarity of a write enable signal to determine an operation (i.e. write or read) on the memory that provides the desired clock latency to the memory. The clock delay circuit may have a low skew portion and a high skew portion. The selection of the high skew portion or low skew portion may depend on the status of the write enable line, such as a polarity or logical value.

Abstract: A device, system, and method select a frequency band during an attenuation activity state. The method is performed at a device that is configured to establish a network connection to a network having a first priority of available frequency bands set by the network. The method includes identifying an attenuation activity state. The method includes generating a second priority of the available frequency bands based on the attenuation activity state. The method includes selecting one of the available frequency bands based on the second priority to establish the network connection.