A method for learning a data embedding network is provided. The method includes steps of: a learning device acquiring and inputting original training data and mark training data into the data embedding network which integrates them and generates marked training data; inputting the marked training data into a learning network which applies a network operation to them and generates 1-st characteristic information, and inputting the original training data into the learning network which applies a network operation to them and generates 2-nd characteristic information; learning the data embedding network such that a data error is minimized, by referring to part of errors referring to the 1-st and the 2-nd characteristic information and errors referring to task specific outputs and their ground truths, and a marked data score is maximized, and learning a discriminator such that a original data score is maximized and the marked data score is minimized.

Various embodiments provide systems and methods for live action gaming. According to one embodiment, a method facilitates scoring for an in-person, live-action game, for example, a projectile-tag scoring game or the like, involving multiple players. A gaming outfit worn by a first player or a projectile launcher of a second player may determine a shot hit by the second player against the first player based at least in part on detection of an impact of a projectile fired by the projectile launcher with the gaming outfit. A score for the in-person, live-action game may then be updated based on the shot hit.

Various embodiments provide systems and methods for live action gaming. According to one embodiment, a method facilitates scoring for an in-person, live-action game, for example, a projectile-tag scoring game or the like, involving multiple players. A gaming outfit worn by a first player or a projectile launcher of a second player may determine a shot hit by the second player against the first player based at least in part on detection of an impact of a projectile fired by the projectile launcher with the gaming outfit. A score for the in-person, live-action game may then be updated based on the shot hit.

A processing unit topology of a neural network including a plurality of processing units is determined. The neural network includes at least one machine in which each machine includes a plurality of nodes, and wherein each node includes at least one of the plurality of processing units. One or more of the processing units are grouped into a first group according to a first affinity. The first group is configured, using a processor and a memory, to use a first aggregation procedure for exchanging model parameters of a model of the neural network between the processing units of the first group. One or more of the processing units are grouped into a second group according to a second affinity. The second group is configured to use a second aggregation procedure for exchanging the model parameters between the processing units of the second group.

A memory device may include a plurality of resistive elements and a control unit for controlling the memory device. The memory device is configured to program single weights of the memory device by groups of at least two resistive elements. A related method and a related computer program product may be also provided.

Methods and apparatus for training a matrix-based differentiable program using a photonics-based processor. The matrix-based differentiable program includes at least one matrix-valued variable associated with a matrix of values in a Euclidean vector space. The method comprises configuring components of the photonics-based processor to represent the matrix of values as an angular representation, processing, using the components of the photonics-based processor, training data to compute an error vector, determining in parallel, at least some gradients of parameters of the angular representation, wherein the determining is based on the error vector and a current input training vector, and updating the matrix of values by updating the angular representation based on the determined gradients.

Methods and apparatus for training a matrix-based differentiable program using a photonics-based processor. The matrix-based differentiable program includes at least one matrix-valued variable associated with a matrix of values in a Euclidean vector space. The method comprises configuring components of the photonics-based processor to represent the matrix of values as an angular representation, processing, using the components of the photonics-based processor, training data to compute an error vector, determining in parallel, at least some gradients of parameters of the angular representation, wherein the determining is based on the error vector and a current input training vector, and updating the matrix of values by updating the angular representation based on the determined gradients.

Reduction in the number of neurons and axons in a neurosynaptic network while maintaining its functionality is provided. A neural network description describing a neural network is read. One or more functional unit of the neural network is identified. The one or more functional unit of the neural network is optimized. An optimized neural network description is written based on the optimized functional unit.

Reduction in the number of neurons and axons in a neurosynaptic network while maintaining its functionality is provided. A neural network description describing a neural network is read. One or more functional unit of the neural network is identified. The one or more functional unit of the neural network is optimized. An optimized neural network description is written based on the optimized functional unit.

A memory device may include a plurality of resistive elements and a control unit for controlling the memory device. The memory device is configured to program single weights of the memory device by groups of at least two resistive elements. A related method and a related computer program product may be also provided.