Abstract: A computing device may be equipped with a generalized framework for accomplishing conditional computation or gating in a neural network. The computing device may receive input in a neural network layer that includes two or more filters. The computing device may intelligently determine whether the two or more filters are relevant to the received input. The computing device may deactivate filters that are determined not to be relevant to the received input (or activate filters that are determined to be relevant to the received input), and apply the received input to active filters in the layer to generate an activation.

Abstract: 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.

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.

Abstract: A lossy data compressor for physical measurement data, comprising a parametrized mapping network hat, when applied to a measurement data point x in a space X, produces a point z in a lower-dimensional manifold Z, and configured to provide a point z on manifold Z as output in response to receiving a data point x as input, wherein the manifold Z is a continuous hypersurface that only admits fully continuous paths between any two points on the hypersurface; and the parameters ? of the mapping network are trainable or trained towards an objective that comprises minimizing, on the manifold Z, a distance between a given prior distribution PZ and a distribution PQ induced on manifold Z by mapping a given set PD of physical measurement data from X onto Z using the mapping network, according to a given distance measure.

Abstract: A neural network may be configured to receive, during a training phase of the neural network, a first input at an input layer of the neural network. The neural network may determine, during the training phase, a first classification at an output layer of the neural network based on the first input. The neural network may adjust, during the training phase and based on a comparison between the determined first classification and an expected classification of the first input, weights for artificial neurons of the neural network based on a loss function. The neural network may output, during an operational phase of the neural network, a second classification determined based on a second input, the second classification being determined by processing the second input through the artificial neurons using the adjusted weights.

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: A method for processing temporally redundant data in an artificial neural network (ANN) includes encoding an input signal, received at an initial layer of the ANN, into an encoded signal. The encoded signal comprises the input signal and a rate of change of the input signal. The method also includes quantizing the encoded signal into integer values and computing an activation signal of a neuron in a next layer of the ANN based on the quantized encoded signal. The method further includes computing an activation signal of a neuron at each layer subsequent to the next layer to compute a full forward pass of the ANN. The method also includes back propagating approximated gradients and updating parameters of the ANN based on an approximate derivative of a loss with respect to the activation signal.

Abstract: A method of computation in a deep neural network includes discretizing input signals and computing a temporal difference of the discrete input signals to produce a discretized temporal difference. The method also includes applying weights of a first layer of the deep neural network to the discretized temporal difference to create an output of a weight matrix. The output of the weight matrix is temporally summed with a previous output of the weight matrix. An activation function is applied to the temporally summed output to create a next input signal to a next layer of the deep neural network.

Abstract: A method for privatizing an iteratively reweighted least squares (IRLS) solution includes perturbing a first moment of a dataset by adding noise and perturbing a second moment of the dataset by adding noise. The method also includes obtaining the IRLS solution based on the perturbed first moment and the perturbed second moment. The method further includes generating a differentially private output based on the IRLS solution.

Abstract: A method of training a neural network with back propagation includes generating error events representing a gradient of a cost function for the neural network. The error events may be generated based on a forward pass through the neural network resulting from input events, weights of the neural network and events from a target signal. The method further includes updating the weights of the neural network based on the error events.

Abstract: Unsupervised learning of object category from images is carried out by using an automatic image recognition system. A plurality of training images are automatically analyzed using an interest operator which produces an indication of features. Those features are clustered using a vector guantizer. The model is learned from the features using expectation maximization to assess a joint probability of which features are most relevant.

Abstract: Unsupervised learning of object category from images is carried out by using an automatic image recognition system. A plurality of training images are automatically analyzed using an interest operator which produces an indication of features. Those features are clustered using a vector quantizer. The model is learned from the features using expectation maximization to assess a joint probability of which features are most relevant.