Abstract: A method performed by a communication device includes generating an initial channel estimate of a channel for a current time step with a Kalman filter based on a first signal received at the communication device. The method also includes inferring, with a neural network, a residual of the initial channel estimate of the current time step. The method further includes updating the initial channel estimate of the current time step based on the residual.

Abstract: 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.

Abstract: Aspects described herein provide a method of processing data, including: receiving a set of global parameters for a plurality of machine learning models; processing data stored locally on an processing device with the plurality of machine learning models according to the set of global parameters to generate a machine learning model output; receiving, at the processing device, user feedback regarding machine learning model output for the plurality of machine learning models; performing an optimization of the plurality of machine learning models based on the machine learning output and the user feedback to generate locally updated machine learning model parameters; sending the locally updated machine learning model parameters to a remote processing device; and receiving a set of globally updated machine learning model parameters for the plurality of machine learning models.

Abstract: A method performs XNOR-equivalent operations by adjusting column thresholds of a compute-in-memory array of an artificial neural network. The method includes adjusting an activation threshold generated for each column of the compute-in-memory array based on a function of a weight value and an activation value. The method also includes calculating a conversion bias current reference based on an input value from an input vector to the compute-in-memory array, the compute-in-memory array being programmed with a set of weights. The adjusted activation threshold and the conversion bias current reference are used as a threshold for determining the output values of the compute-in-memory array.

Abstract: A method for quantizing a neural network includes modeling noise of parameters of the neural network. The method also includes assigning grid values to each realization of the parameters according to a concrete distribution that depends on a local fixed-point quantization grid and the modeled noise and. The method further includes computing a fixed-point value representing parameters of a hard fixed-point quantized neural network.

Abstract: In one embodiment, an electronic device includes a compute-in-memory (CIM) array that includes a plurality of columns. Each column includes a plurality of CIM cells connected to a corresponding read bitline, a plurality of offset cells configured to provide a programmable offset value for the column, and an analog-to-digital converter (ADC) having the corresponding bitline as a first input and configured to receive the programmable offset value. Each CIM cell is configured to store a corresponding weight.

Abstract: 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.

Abstract: Certain aspects of the present disclosure provide techniques for training and inferencing with machine learning localization models. In one aspect, a method, includes training a machine learning model based on input data for performing localization of an object in a target space, including: determining parameters of a neural network configured to map samples in an input space based on the input data to samples in an intrinsic space; and determining parameters of a coupling matrix configured to transport the samples in the intrinsic space to the target space.

Abstract: A processor-implemented method is presented. The method includes receiving an input sequence comprising a group of channel dynamics observations for a wireless communication channel. Each channel dynamics observation may correspond to a timing of a group of timings. The method also includes determining, via a recurrent neural network (RNN), a residual at each of the group of timings based on the group of channel dynamics observations. The method further includes updating Kalman filter (KF) parameters based on the residual and estimating, via the KF, a channel state based on the updated KF parameters.

Abstract: A system for adapting a base classifier to one or more novel classes. The base classifier classifies an instance into a base class by extracting a feature representation from the instance using a feature extractor and matching it to class representations of the base classes. The base classifier is adapted using training data for the novel classes. Class representations of the novel classes are determined based on feature representations of instances of the novel classes. The class representations of the novel and base classes are then adapted, wherein at least one class representation of a novel class is adapted based on a class representation of a base class and at least one class representation of a base class is adapted based on a class representation of a novel class. The adapted class representations of the base and novel classes are associated with the base classifier.

Abstract: 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.

Abstract: Certain aspects of the present disclosure provide techniques for object positioning using mixture density networks, comprising: receiving radio frequency (RF) signal data collected in a physical space; generating a feature vector encoding the RF signal data by processing the RF signal data using a first neural network; processing the feature vector using a first mixture model to generate a first encoding tensor indicating a set of moving objects in the physical space, a first location tensor indicating a location of each of the moving objects in the physical space, and a first uncertainty tensor indicating uncertainty of the locations of each of the moving objects in the physical space; and outputting at least one location from the first location tensor.

Abstract: A computer-implemented method. The method includes: receiving or knowing an input graph that comprises nodes and associated multi-dimensional coordinates, and propagating the input graph through a trained graph neural network, the input graph being provided as input to an input section of the trained graph neural network, wherein an output tensor of at least one hidden layer of the trained graph neural network is determined, at least partly, based on a set of node embeddings of a previous layer and based on coordinate embeddings associated with the node embeddings of the previous layer, and wherein an output graph is provided in an output section of the trained graph neural network.

Abstract: Certain aspects of the present disclosure provide techniques for performing probabilistic convolution operation with a quantum and non-quantum processing systems.

Abstract: A method performed by an artificial neural network includes determining a conditional probability distribution representing a channel based on a data set of transmit and receive sequences. The method also includes determining a latent representation of the channel based on the conditional probability distribution. The method further includes performing a channel-based function based on the latent representation.

Abstract: 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.

Abstract: Certain aspects of the present disclosure provide techniques for performing operations with probabilistic numeric convolutional neural network, including: defining a Gaussian Process based on a mean and a covariance of input data; applying a linear operator to the Gaussian Process to generate pre-activation data; applying a nonlinear operation to the pre-activation data to form activation data; and applying a pooling operation to the activation data to generate an inference.

Abstract: A computer-implemented method for training a normalizing flow. The normalizing flow is configured to determine a first output signal characterizing a likelihood or a log-likelihood of an input signal. The normalizing flow includes at least one first layer which includes trainable parameters. A layer input to the first layer is based on the input signal and the first output signal is based on a layer output of the first layer. The training includes: determining at least one training input signal; determining a training output signal for each training input signal using the normalizing flow; determining a first loss value which is based on a likelihood or a log-likelihood of the at least one determined training output signal with respect to a predefined probability distribution; determining an approximation of a gradient of the trainable parameters; updating the trainable parameters of the first layer based on the approximation of the gradient.

Abstract: 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.

Abstract: Computer implemented method for digital image data, digital video data or digital audio data enhancement, and a computer implemented method for encoding or decoding this data in particular for transmission or storage, wherein an element representing a part of said digital data comprises an indication of a position of the element in an ordered input data of a plurality of data elements, wherein a plurality of elements is transformed to a representation depending on an invertible linear mapping, wherein the invertible linear mapping maps the input of the plurality of elements to the representation, wherein the invertible linear mapping comprises at least one autoregressive convolution.