Abstract: A client device configured with a neural network includes a processor, a memory, a user interface, a communications interface, a power supply and an input device, wherein the memory includes a trained neural network received from a server system that has trained and configured the neural network for the client device. A server system and a method of training a neural network are disclosed.

Abstract: A Dynamic Vision Sensor (DVS) pose-estimation system includes a DVS, a transformation estimator, an inertial measurement unit (IMU) and a camera-pose estimator based on sensor fusion. The DVS detects DVS events and shapes frames based on a number of accumulated DVS events. The transformation estimator estimates a 3D transformation of the DVS camera based on an estimated depth and matches confidence-level values within a camera-projection model such that at least one of a plurality of DVS events detected during a first frame corresponds to a DVS event detected during a second subsequent frame. The IMU detects inertial movements of the DVS with respect to world coordinates between the first and second frames. The camera-pose estimator combines information from a change in a pose of the camera-projection model between the first frame and the second frame based on the estimated transformation and the detected inertial movements of the DVS.

Abstract: A device includes a wireless communication circuit and one or more processors operable with the wireless communication circuit. The wireless communication circuit receives one or more local area wireless communication signals identifying one or more external electronic devices operating within an environment of the device. The one or more processors select a local area wireless communication signal having a power magnitude experiencing a highest amount of change from the one or more local area wireless communication signals and perform a pairing operation with an external device identified by the local area wireless communication signal.

Abstract: An image signal processing (ISP) system is provided. The system includes a neural network trained by inputting a set of raw data images and a correlating set of desired quality output images; the neural network including an input for receiving input image data and providing processed output; wherein the processed output includes input image data that has been adjusted for at least one image quality attribute. A method and an imaging device are disclosed.

Abstract: A method of manufacturing an apparatus and a method of constructing an integrated circuit are provided. The method of manufacturing an apparatus includes forming the apparatus on a wafer or a package with at least one other apparatus, wherein the apparatus comprises a polynomial generator, a first matrix generator, a second matrix generator, a third matrix generator, and a convolution generator; and testing the apparatus, wherein testing the apparatus comprises testing the apparatus using one or more electrical to optical converters, one or more optical splitters that split an optical signal into two or more optical signals, and one or more optical to electrical converters.

Abstract: A method for configuring a neural network is provided. The method includes: selecting a neural network including a plurality of layers, each of the layers including a plurality of neurons for processing an input and providing an output; and, incorporating at least one switch configured to randomly select and disable at least a portion of the neurons in each layer. Another method in the computer program product is disclosed.

Abstract: A client device configured with a neural network includes a processor, a memory, a user interface, a communications interface, a power supply and an input device, wherein the memory includes a trained neural network received from a server system that has trained and configured the neural network for the client device. A server system and a method of training a neural network are disclosed.

Abstract: An electronic device includes one or more low-power context sensors, one or more high-power context sensors, and one or more processors operable with the one or more low-power context sensors and the one or more high-power context sensors. The one or more processors, working with context engines associated with the sensors, minimize usage of the high-power context sensors when determining a context of the electronic device, where that determined context has a confidence score above a predefined confidence level threshold.

Abstract: An apparatus and a method is provided. The apparatus includes a polynomial generator, including an input and an output; a first matrix generator, including an input connected to the output of the polynomial generator, and an output; a second matrix generator, including an input connected to the output of the first matrix generator, and an output; a third matrix generator, including a first input connected to the output of the first matrix generator, a second input connected to the output of the second matrix generator, and an output; and a convolution generator, including an input connected to the output of the third matrix generator, and an output.

Abstract: Systems and methods for authenticating a user of a mobile communications device entail scanning an environment of the mobile device with a low power sensor and detecting a nearby person via the first sensor. In response, a higher power sensor is activated and the person is authenticated via the second sensor using a first authentication mechanism. A first level of access is granted to the person at this point. When the person moves to within a first threshold distance of the device, the person is authenticated using a second more secure authentication mechanism, and a second, higher, level of access is granted to the person.

Abstract: Systems and methods for enhancing the operation of a mobile communications device include detecting another device travelling to the same destination as the user's device, pairing the devices, collect context data for the user's device, and transmitting the context data to the other device. The user's device also receives context data from the other device and applies that context data to improve operation of the user's device.

Abstract: Systems and methods for providing event media distribution associated with an event to a user include receiving an electronic invitation to the event having a time and location associated therewith and displaying the electronic invitation, including a response option and one or more mode options. The mode options are associated with one or more rules regarding automatic sharing of media associated with the event. The user may give an affirmative response that they will attend, as well as a selection of one or more mode options. When user of the mobile communications device is present at the event, the user device shares information to and from the devices of other attendees in accordance with the selected mode option(s).

Abstract: A method is disclosed to reduce computational load of a deep neural network. A number of multiply-accumulate (MAC) operations is determined for each layer of the deep neural network. A pruning error allowance per weight is determined based on a computational load of each layer. For each layer of the deep neural network: a threshold estimator is initialized, and weights of each layer are pruned based on a standard deviation of all weights within the layer. A pruning error per weight is determined for the layer, and if the pruning error per weight exceeds a predetermined threshold, the threshold estimator is updated for the layer the weights of the layer are repruned using the updated threshold estimator and the pruning error per weight is re-determined until the pruning error per weight is less than the threshold. The deep neural network is then retrained.

Abstract: An apparatus and a method. The apparatus includes a dynamic vision sensor (DVS) configured to generate a stream of events, where an event includes a location and a binary value indicating a positive or a negative change in luminance; a sampling unit connected to the DVS and configured to sample the stream of events; and an image formation unit connected to the sampling unit and configured to form an image for each sample of the stream of events, wherein a manner of sampling by the sampling unit is adjusted to reduce variations between images formed by the image formation unit.

Abstract: An embodiment includes a method, comprising: pruning a layer of a neural network having multiple layers using a threshold; and repeating the pruning of the layer of the neural network using a different threshold until a pruning error of the pruned layer reaches a pruning error allowance.

Abstract: A system and method to reduce weight storage bits for a deep-learning network includes a quantizing module and a cluster-number reduction module. The quantizing module quantizes neural weights of each quantization layer of the deep-learning network. The cluster-number reduction module reduces the predetermined number of clusters for a layer having a clustering error that is a minimum of the clustering errors of the plurality of quantization layers. The quantizing module requantizes the layer based on the reduced predetermined number of clusters for the layer and the cluster-number reduction module further determines another layer having a clustering error that is a minimum of the clustering errors of the plurality of quantized layers and reduces the predetermined number of clusters for the another layer until a recognition performance of the deep-learning network has been reduced by a predetermined threshold.

Abstract: A Dynamic Vision Sensor (DVS) pose-estimation system includes a DVS, a transformation estimator, an inertial measurement unit (IMU) and a camera-pose estimator based on sensor fusion. The DVS detects DVS events and shapes frames based on a number of accumulated DVS events. The transformation estimator estimates a 3D transformation of the DVS camera based on an estimated depth and matches confidence-level values within a camera-projection model such that at least one of a plurality of DVS events detected during a first frame corresponds to a DVS event detected during a second subsequent frame. The IMU detects inertial movements of the DVS with respect to world coordinates between the first and second frames. The camera-pose estimator combines information from a change in a pose of the camera-projection model between the first frame and the second frame based on the estimated transformation and the detected inertial movements of the DVS.

Abstract: An apparatus and a method. The apparatus includes an image representation unit configured to receive a sequence of frames generated from events sensed by a dynamic vision sensor (DVS) and generate a confidence map from non-noise events; and an image denoising unit connected to the image representation unit and configured to denoise an image in a spatio-temporal domain. The method includes receiving, by an image representation unit, a sequence of frames generated from events sensed by a DVS, and generating a confidence map from non-noise events; and denoising, by an image denoising unit connected to the image representation unit, images formed from the frames in a spatio-temporal domain.

Abstract: A neural network is trained to generate feature maps and associated weights. Reordering is performed to generate a functionally equivalent network. The reordering may be performed to improve at least one of compression of the weights, load balancing, and execution. In one implementation, zero value weights are grouped, permitting them to be skipped during execution.

Abstract: An apparatus and a method. The apparatus includes an image representation unit configured to receive a sequence of frames generated from events sensed by a dynamic vision sensor (DVS) and generate a confidence map from non-noise events; and an image denoising unit connected to the image representation unit and configured to denoise an image in a spatio-temporal domain. The method includes receiving, by an image representation unit, a sequence of frames generated from events sensed by a DVS, and generating a confidence map from non-noise events; and denoising, by an image denoising unit connected to the image representation unit, images formed from the frames in a spatio-temporal domain.