Robert Boschgmbh

Qualcomm Incorporated

Qualcomm Technologies, Inc.

Sap Se

Max Welling

Arash Behboodi

Emiel Hoogeboom

Joseph Binamira Soriaga

Priyank Jaini

Anna Khoreva

Thomas Andy Keller

Edward Harrison Teague

Zhongze Wang

Jorn Peters

Taco Sebastiaan Cohen

Dan Zhang

Farhad Ghazvinian Zanjani

Michael Herman

Herke Van Hoof

Kumar Pratik

Matthias Reisser

Roberto Bondesan

Rana Ali Amjad

Zeynep Akata

Didrik Nielsen

Frans Adriaan Oliehoek

Patrick Forré

Elise Van Der Pol

Taesang Yoo

Simone Merlin

Xiaochun Zhu

Lorenzo Ferrari

Efstratios Gavves

Martin Schiegg

Volker Fischer

Daniel Hendricus Franciscus Dijkman

Tijmen Pieter Frederik Blankevoort

Ilia Karmanov

William Harris Beluch

Maja Rudolph

Christos Louizos

Filipe Condessa

Melih Kandemir

Gabriele Cesa

Xiahan Shi

Pim De Haan

Jakub Mikolaj Tomczak

Karim Said Mahmoud Barsim

Tim Genewein

Daniel Worrall

Kaspar Sakmann

Tribhuvanesh Orekondy

Sindy Lowe

Mirgahney Husham Awadelkareem Mohamed

Victor Garcia Satorras

Maurice Weiler

Lars Holdijk

Simeng Zheng

Shreya Kadambi

Changyong Oh

Jakub Tomczak

Saurabh Kedar Pitre

Leonard Salewski

Mijung Park

Giorgio Patrini

Marcello Carioni

Carioni Marcello

RJH Forré

Certain aspects of the present disclosure provide techniques for processing data in a quantum deformed binary neural network, including: determining an input state for a layer of the quantum deformed binary neural network; computing a mean and variance for one or more observables in the layer; and returning an output activation probability based on the mean and variance for the one or more observables in the layer.

Quantum deformed binary neural networks

Device and method for training an artificial neural network, including providing a neural network layer for an equivariant feature mapping having a plurality of output channels, grouping channels of the output channels into a number of distinct groups, wherein the output channels of each individual distinct group are organized into an individual grid defining a spatial location of each of the output channels of the individual distinct group in the grid for the individual distinct group, providing for each of the output channels of each individual distinct group, a distinct normalization function which is defined depending on the spatial location of the output channel in the grid in that this output channel is organized and depending on tunable hyperparameters for the normalization function, determining an output of the artificial neural network depending on a result of each of the distinct normalization functions, training the hyperparameters of the artificial neural network.

Device and computer implemented method for training an artificial neural network using channel groups

Certain aspects of the present disclosure provide methods, apparatus, and systems for predicting a location of a device in a spatial environment using a machine learning model. An example method generally includes measuring a plurality of signals received from a network entity at a device. A channel state information (CSI) measurement is generated from the measured plurality of signals. Generally, the CSI measurement includes a multipath component. Positions of one or more anchors in a spatial environment are identified based on a machine learning model trained to identify the positions of the one or more anchors based on the CSI measurement. A location of the device is estimated based on the identified positions of the one or more anchors.

Unsupervised location estimation and mapping based on multipath measurements

A computer-implemented method of training an image classifier which uses any combination of labelled and/or unlabelled training images. The image classifier comprises a set of transformations between respective transformation inputs and transformation outputs. An inverse model is defined in which for a deterministic, non-injective transformation of the image classifier, its inverse is approximated by a stochastic inverse transformation. During training, for a given training image, a likelihood contribution for this transformation is determined based on a probability of its transformation inputs being generated by the stochastic inverse transformation given its transformation outputs. This likelihood contribution is used to determine a log-likelihood for the training image to be maximized (and its label, if the training image is labelled), based on which the model parameters are optimized.

Image classifier comprising a non-injective transformation

Certain aspects of the present disclosure provide a method of performing machine learning, comprising: generating a neural network model; and training the neural network model for a task with a first set of input data, wherein: the training uses a total loss functionincluding an equivariance loss componentaccording to=+α, and α>0.

Data and compute efficient equivariant convolutional networks

A computer-implemented system and method relate to object discovery. The system and method include receiving a source image and generating input data by associating each pixel of the source image with predetermined phase values. An encoder encodes the input data to generate latent representation data in spherical coordinates. A decoder decodes the latent representation data to generate spherical reconstruction data of the source image. The spherical reconstruction data includes a radial component and a plurality of phase components. A reconstructed image is generated based at least on the radial component. The reconstructed image is a reconstruction of the source image.

System and method with spherical autoencoder for object discovery

A computer-implemented method of training a machine learnable model for controlling and/or monitoring a computer-controlled system. The machine learnable model is configured to make inferences based on a probability distribution of sensor data of the computer-controlled system. The machine learnable model is configured to account for symmetries in the probability distribution imposed by the system and/or its environment. The training involves sampling multiple samples of the sensor data according to the probability distribution. Initial values are sampled from a source probability distribution invariant to the one or more symmetries. The samples are iteratively evolved according to a kernel function equivariant to the one or more symmetries. The evolution uses an attraction term and a repulsion term that are defined for a selected sample in terms of gradient directions of the probability distribution and of the kernel function for the multiple samples.

Machine learning based on a probability distribution of sensor data

A method for training a neural network. The neural network comprises a first layer which includes a plurality of filters to provide a first layer output comprising a plurality of feature maps. Training of the classifier includes: receiving, by a preceding layer, a first layer input in the first layer, wherein the first layer input is based on the input signal; determining the first layer output based on the first layer input and a plurality of parameters of the first layer; determining a first layer loss value based on the first layer output, wherein the first layer loss value characterizes a degree of dependency between the feature maps, the first layer loss value being obtained in an unsupervised fashion; and training the neural network. The training includes an adaption of the parameters of the first layer, the adaption being based on the first layer loss value.

Device and method for training a neuronal network

A method of training an artificial neural network (ANN), receives, from a base station, signal information for a radio frequency signal between the base station and a user equipment (UE). The artificial neural network is trained to determine a location of the UE and to map the environment based on the received signal information and in the absence of labeled data.

Unsupervised learning for simultaneous localization and mapping in deep neural networks using channel state information

A method for configuring a neural network which is designed to map measured data to one or more output variables. The method includes: transformation(s) of the measured data is/are specified which when applied to the measured data, is/are meant to induce the output variables supplied by the neural network to exhibit an invariant or equivariant behavior; at least one equation is set up which links a condition that the desired invariance or equivariance be given with the architecture of the neural network; by solving the at least one equation a feature is obtained that characterizes the desired architecture and/or a distribution of weights of the neural network in at least one location of this architecture; a neural network is configured in such a way that its architecture and/or its distribution of weights in at least one location of this architecture has/have all of the features ascertained in this way.

Configuring a neural network for equivariant or invariant behavior

Certain aspects of the present disclosure provide a method for performing machine learning, comprising: determining a plurality of vertices in a neighborhood associated with a mesh including a target vertex; determining a linear transformation configured to parallel transport signals along all edges in the mesh to the target vertex; applying the linear transformation to the plurality of vertices in the neighborhood to form a combined signal at the target vertex; determining a set of basis filters; linearly combining the basis filters using a set of learned parameters to form a gauge equivariant convolution filter, wherein the gauge equivariant convolution filter is constrained to maintain gauge equivariance; applying the gauge equivariant convolution filter to the combined signal to form an intermediate output; and applying a nonlinearity to the intermediate output to form a convolution output.

Gauge equivariant geometric graph convolutional neural network

Some embodiments are directed to a computer-implemented method of interacting with a physical environment according to a policy. The policy determines multiple action probabilities of respective actions based on an observable state of the physical environment. The policy includes a neural network parameterized by a set of parameters. The neural network determines the action probabilities by determining a final layer input from an observable state and applying a final layer of the neural network to the final layer input. The final layer is applied by applying a linear combination of a set of equivariant base weight matrices to the final layer input. The base weight matrices are equivariant in the sense that, for a set of multiple predefined transformations of the final layer input, each transformation causes a corresponding predefined action permutation of the base weight matrix output for the final layer input.

Physical environment interaction with an equivariant policy

A device and a method for generating a compressed network from a trained neural network are provided. The method includes: a model generating a compressing map from first training data, the compressing map representing the impact of model components of the model to first output data in response to the first training data; generating a compressed network by compressing the trained neural network in accordance with the compressing map; the trained neural network generating trained network output data in response to second training data; the compressed network generating compressed network output data in response to the second training data; training the model by comparing the trained network output data with the compressed network output data.

Device and method for generating a compressed network from a trained neural network

A computer-implemented method of training an image generation model. The image generation model comprises an argmax transformation configured to compute a discrete index feature indicating an index of a feature of the continuous feature vector with an extreme value. The image generation model is trained using a log-likelihood optimization. This involves obtaining a value of the index feature for the training image, sampling values of the continuous feature vector given the value of the index feature according to a stochastic inverse transformation of the argmax transformation, and determining a likelihood contribution of the argmax transformation for the log-likelihood based on a probability that the stochastic inverse transformation generates the values of the continuous feature vector given the value of the index feature.

Image generation model based on log-likelihood

A computer-implemented method for training a normalizing flow. The normalizing flow predicts a first density value based on a first input image. The first density value characterizes a likelihood of the first input image to occur. The first density value is predicted based on an intermediate output of a first convolutional layer of the normalizing flow. The intermediate output is determined based on a plurality of weights of the first convolutional layer. The method for training includes: determining a second input image; determining an output, wherein the output is determined by providing the second input image to the normalizing flow and providing an output of the normalizing flow as output; determining a second density value based on the output tensor and on the plurality of weights; determining a natural gradient of the plurality of weights with respect to the second density value; adapting the weights according to the natural gradient.

Device and method for training a normalizing flow

Growing community of inventors

Bussum, Netherlands

Max Welling