Abstract: Artificial neural networks (ANNs) are computing systems that imitate a human brain by learning to perform tasks by considering examples. By representing an artificial neural network utilizing individual paths each connecting an input of the ANN to an output of the ANN, a complexity of the ANN may be reduced, and the ANN may be trained and implemented in a much faster manner when compared to an implementation using fully connected ANN graphs.

Abstract: Various embodiments and implementations of graph-neural-network (GNN)-based decoding applications are disclosed. The GNN-based decoding schemes are broadly applicable to different coding schemes, and capable of operating on both binary and non-binary codewords, in different implementations. Advantageously, the inventive GNN-based decoding is scalable, even with arbitrary block lengths, and not subject to typical limits with respect to dimensionality. Decoding performance of the inventive GNN-based techniques demonstrably matches or outpaces BCH and LDPC (both regular and 5G NR) decoding algorithms, while exhibiting improvements with respect to number of iterations required and scalability of the GNN-based approach. These inventive concepts are implemented, according to various embodiments, as methods, systems, and computer program products.

Abstract: One embodiment of a method for generating representations of scenes includes assigning each image included in a set of images of a scene to one or more clusters of images based on a camera pose associated with the image, and performing one or more operations to generate, for each cluster included in the one or more clusters, a corresponding three-dimensional (3D) representation of the scene based on one or more images assigned to the cluster.

Abstract: Disclosed are apparatuses, systems, and techniques that may use machine learning for determining transmitted signals in communication systems that deploy orthogonal frequency division multiplexing. A system for performing the disclosed techniques includes receiving (RX) antennas to receive RX signals, each RX signal received over a respective resource element of a resource grid. Individual resource elements of the resource grid are associated with different radio subcarriers and/or data symbols. The RX signals include a combination of a plurality of transmitted (TX) streams. The system further includes a processing device to process the RX signals using one or more neural network models to determine TX data symbols transmitted via the plurality of TX streams.

Abstract: A component for a projection exposure apparatus for semiconductor lithography, comprises an optical element and an actuator, which are force-fittingly connected to each other. The actuator at least locally deforms the optical element. The actuator can be configured to minimize the loss in rigidity at the peripheries delimiting the actuator on the imaging quality. A method for designing a component of projection exposure apparatus is provided.

Abstract: Various embodiments and implementations of graph-neural-network (GNN)-based decoding applications are disclosed. The GNN-based decoding schemes are broadly applicable to different coding schemes, and capable of operating on both binary and non-binary codewords, in different implementations. Advantageously, the inventive GNN-based decoding is scalable, even with arbitrary block lengths, and not subject to typical limits with respect to dimensionality. Decoding performance of the inventive GNN-based techniques demonstrably matches or outpaces BCH and LDPC (both regular and 5G NR) decoding algorithms, while exhibiting improvements with respect to number of iterations required and scalability of the GNN-based approach. These inventive concepts are implemented, according to various embodiments, as methods, systems, and computer program products.

Abstract: Neural network-based structures for action user equipment device detection, estimation of time-of-arrival, and estimation of carrier frequency offset utilized with the narrowband physical random-access channel of wireless communication systems. The structure includes a neural network to generate predictions of active user equipment devices, and a twin neural network to generate time-of-arrival predictions for signals from the user equipment devices and carrier frequency offset predictions for signals from the user equipment devices.

Abstract: Various embodiments of mounting structures for solar photovoltaic (PV) modules and methods for constructing such mounting structures are described. A mounting structure is usable to secure PV modules in portrait orientation or landscape orientation. PV modules are secured to PV module support rails, which may be secured to purlins of a mounting structure using clamps. In some embodiments, self-adhesive grounding patches are used to establish electrical grounding paths in various embodiments of mounting structure.

Abstract: An example method of correcting a defect in a seat comprises the steps of: (a) imaging a seat to obtain an image of the seat, a portion of the seat having a defect; (b) applying a localized boundary around the portion of the seat having the defect within the image of the seat; (c) translating the localized boundary into a seat specific map of a baseline model of the seat such that a portion of the baseline model of the seat that corresponds to the portion of the seat having the defect within the image of the seat is disposed within a translated localized boundary; (d) selecting a predetermined path for an automated device to correct the portion of the seat having the defect based on the portion of the baseline model of the seat; and (e) correcting the portion of the seat having the defect.

Abstract: Various embodiments of mounting structures for solar photovoltaic (PV) modules and methods for constructing such mounting structures are described. A mounting structure is usable to secure PV modules in portrait orientation or landscape orientation. PV modules are secured to PV module support rails, which may be secured to purlins of a mounting structure using clamps. In some embodiments, self-adhesive grounding patches are used to establish electrical grounding paths in various embodiments of mounting structure.

Abstract: An example method of correcting a defect in a seat comprises the steps of: (a) imaging a seat to obtain an image of the seat, a portion of the seat having a defect; (b) applying a localized boundary around the portion of the seat having the defect within the image of the seat; (c) translating the localized boundary into a seat specific map of a baseline model of the seat such that a portion of the baseline model of the seat that corresponds to the portion of the seat having the defect within the image of the seat is disposed within a translated localized boundary; (d) selecting a predetermined path for an automated device to correct the portion of the seat having the defect based on the portion of the baseline model of the seat; and (e) correcting the portion of the seat having the defect.

Abstract: The invention relates to a dispenser 20 for the spray delivery of a preparation 18. The dispenser comprises: a reservoir 22 suitable for containing the preparation 18, a mechanical pump 24, a load chamber 26, a nozzle 28 having a delivery axis, and a delivery cone 30 having an axis. The mechanical pump is able, whenever operated: to take a predetermined amount of preparation from the reservoir, to supply said amount of preparation to the load chamber upstream of the nozzle, and to create a delivery pressure in the load chamber. The nozzle is able to deliver said amount of preparation in the form of an aerosol spray 180. The dispenser according to the invention is characterized in that the delivery cone comprises, in the proximity of the nozzle, at least one through-hole 320 suitable for putting the inside of the delivery cone into communication with the surrounding environment.

Abstract: Artificial neural networks (ANNs) are computing systems that imitate a human brain by learning to perform tasks by considering examples. By representing an artificial neural network utilizing individual paths each connecting an input of the ANN to an output of the ANN, a complexity of the ANN may be reduced, and the ANN may be trained and implemented in a much faster manner when compared to an implementation using fully connected ANN graphs.

Abstract: Artificial neural networks (ANNs) are computing systems that imitate a human brain by learning to perform tasks by considering examples. These ANNs are typically created by connecting several layers of neural units using connections, where each neural unit is connected to every other neural unit either directly or indirectly to create fully connected layers within the ANN. However, by representing an artificial neural network utilizing paths from an input of the ANN to an output of the ANN, a complexity of the ANN may be reduced, and the ANN may be trained and implemented in a much faster manner when compared to fully connected layers within the ANN. More specifically, the ANN may be trained sparse from scratch in order to avoid a more expensive procedure of training the ANN and compressing it afterwards.

Abstract: Artificial neural networks (ANNs) are computing systems that imitate a human brain by learning to perform tasks by considering examples. By representing an artificial neural network utilizing individual paths each connecting an input of the ANN to an output of the ANN, a complexity of the ANN may be reduced, and the ANN may be trained and implemented in a much faster manner when compared to an implementation using fully connected ANN graphs.

Abstract: Artificial neural networks (ANNs) are computing systems inspired by the human brain by learning to perform tasks by considering examples. These ANNs are typically created by connecting several layers of artificial neurons using connections, where each artificial neuron is connected to every other artificial neuron either directly or indirectly to create fully connected layers within the ANN. By substituting ternary matrices for one or more fully connected layers within the ANN, a complexity and resource usage of the ANN may be reduced, while improving the performance of the ANN.

Abstract: A siding material for a building configured to hold one or more solar panels is disclosed including a siding shell including a first section and/or a second section, wherein each first and/or second section includes an essentially flat face disposed at an angle ranging from about 30 degrees to about 90 degrees relative to the ground or a perpendicular plane extending from a side of the building. In addition, one or more surfaces of the first section and/or the second section are perforated, and the first section and/or the second section each include a channel configured to hold an electrical cable.

Abstract: Various embodiments of mounting structures for solar photovoltaic (PV) modules and methods for constructing such mounting structures are described. A mounting structure is usable to secure PV modules in portrait orientation or landscape orientation. PV modules are secured to PV module support rails, which may be secured to purlins of a mounting structure using clamps. In some embodiments, self-adhesive grounding patches are used to establish electrical grounding paths in various embodiments of mounting structure.