Abstract: Methods and apparatus for reducing a size of a neural network model, the method including: compressing data of the neural network model; identifying structure information of a vector register, wherein the structure information includes a number of registers included in the vector register; comparing a number of elements in the compressed data with a first condition, wherein the first condition is determined based on the number of registers in the vector register; and in response to the number of elements satisfying the first condition, associating the compressed data with the vector register to enable loading the compressed data to the vector register.

Abstract: The present disclosure relates to a method for scheduling a computation graph on a processing in memory (PIM) enabled device comprising a memory block assembly. The method comprises allocating a first node of the computation graph on a first memory block of a first array of memory blocks in the memory block assembly and allocating a second node of the computation graph on a second memory block of a second array of memory blocks in the memory block assembly, wherein output data of the first node is used for executing the second node. The memory block assembly can be configured to support data transfer from the first memory block to the second memory block via an internal data coupling in the memory block assembly.

Abstract: A superhydrophobic coating is provided and contains organosilane, an inorganic nanomaterial, and an emulsifying agent. A mass proportion of the components is controlled, so that the superhydrophobic coating can form a micro-nano mixed microstructure inside foam concrete. The organosilane first forms dense hydrophobic surface layers on the surface and in inner pores of the foam concrete, and the nanomaterial forms uniformly distributed nano-bulges on the hydrophobic surface layers formed by the silane. The superhydrophobic performance of the foam concrete can be effectively improved by combining the two microstructures. The foam concrete exhibits excellent superhydrophobic performance.

Abstract: A pressing device includes a screw body. The screw body includes a screw head that comprises a driver interface. The screw body also includes a screw shaft that comprises a screw tip opposite the screw head with respect to the screw shaft, exterior spiral threads between the screw head and screw tip, and an interior cavity with an opening at the screw tip. The pressing device also includes a pin partially inserted into the interior cavity. The pin comprises a first pin end inserted into the interior cavity, a pin shaft that is connected to the first pin end, and a second pin end that is connected to the pin shaft and that is exterior to the interior cavity. Applying a force to the second pin end in a direction towards the screw head causes the pin shaft to advance into to interior cavity.

Abstract: The present disclosure relates to a processing in memory (PIM) enabled device for executing a neural network model. The PIM enabled device comprises a memory block assembly comprising a first array of memory blocks, a second array of memory blocks adjacent to the first array of memory blocks, a plurality of first data links associated with the first array of memory blocks and the second array of memory blocks, wherein each data link of the plurality of first data links communicatively couples two corresponding memory blocks of which are from the first array of memory blocks and the second array of memory blocks respectively, and a second data link communicatively coupled to the plurality of first data links. The data from a first memory block of the first array of memory blocks can be transferable to a second memory block of the second array of memory blocks via the plurality of first data links and the second data link.

Abstract: A control apparatus controls an agent apparatus functioning as a user interface of a request processing apparatus that acquires a request indicated by at least one of a voice and a gesture of a user and performs a process corresponding to the request. The control apparatus includes a gaze point specifying section specifying a gaze point of the user, and a face control section controlling an orientation of a face or line of sight of an agent used to transmit information to the user. The face control section controls the orientation of the face or line of sight of the agent such that the face or line of sight of the agent becomes oriented toward the user, if the gaze point is positioned at (i) a portion of the agent or (ii) a portion of an image output section that displays or projects an image of the agent.

Abstract: System and methods for solder void analysis with an optical inspection component are described, including a plurality of optical fibers longitudinally disposed through a glass tube such that ends of the optical fibers are exposed from corresponding ends of the glass tube. A solderable fill encompassing each of the optical fibers by filling spaces between each of the optical fibers and between the optical fibers and the glass tube such that the ends of the glass tube include the ends of the optical fibers surrounded by the solderable fill to form an interface around the optical fibers for soldering one of the ends of the glass tube to a solder pad.

Abstract: A system for flux residue detection is provided. The system includes a flux heater, where the flux heater controls a temperature of a flux spray applied to a printed circuit board, and an infrared camera, wherein the infrared camera provides a thermal image of the flux on the printed circuit board. A method, a computer system, and a computer program product for flux residue detection is provided, including setting flux application parameters, applying flux to a printed circuit board, and capturing an infrared image of the flux applied to the printed circuit board. A method, a computer system, and a computer program product for flux residue detection is provided, including setting flux application parameters, applying flux to a printed circuit board, capturing an infrared image of the flux applied to the printed circuit board, and determining there is excess flux residue on the printed circuit board.

Abstract: An operation control device includes a line-of-sight detector configured to detect a line of sight of a driver of a vehicle on the basis of an image of an interior of the vehicle captured by an imaging device provided in the vehicle, a hand state detector configured to detect a hand state of the driver on the basis of the image, a driving state determiner configured to determine whether the detected hand state is a first state in which it is estimated that a driving operation of the vehicle is being performed or a second state in which it is estimated that the driving operation is not being performed, a traveling state detector configured to detect a traveling state of the vehicle, and an operation restrictor configured to restrict reception of an operation on an operator including a display device arranged within the vehicle.

Abstract: A disc-type speed regulation magnetic coupler based on bevel gear drive is provided, consisting of a driving disc assembly and a driven disc assembly, wherein a speed regulation device is mounted on the driving disc assembly.

Abstract: According to some embodiments, a socket for an electronic device includes a housing and pins connected to the housing. The housing includes a base extending laterally and having an inner face and an outer face; a riser connected to the base and extending away from the outer face; a wall extending laterally, connected to the riser, and having an exterior face and an interior face that faces the outer face of the base; mounting ports extending through the base from the inner face to the outer face; and exit ports extending through the wall from the interior face to the exterior face. Each pin includes a portion extending at least partially though one mounting port; a portion extending between the base and the wall; and a portion extending through one exit port.

Abstract: The present disclosure relates to a method for detecting error in executing a computation graph on heterogeneous computing devices. The method comprises receiving a first reference value as an execution result for a first node of the computation graph from a reference device included in the heterogeneous computing devices, receiving a first target value from a target device included in the heterogeneous computing devices as an execution result by the target device for the first node, comparing the first reference value and the first target value, and determining whether the first target value is in error based on the comparison of the first reference value and the first target value. The method can further comprise generating multiple execution contexts for executing the computation graph on the heterogeneous computing devices.

Abstract: The present disclosure relates to a method for scheduling a computation graph on heterogeneous computing resources. The method comprises generating an augmented computation graph that includes a first set of replica nodes corresponding to a first node in the computation graph and a second set of replica nodes corresponding to a second node in the computation graph, wherein the replica nodes of the first set are connected by edges to the replica nodes of the second set according to dependency between the first node and the second node in the computation graph, adapting the augmented computation graph to include performance values for the edges, the replica nodes of the first set, and the replica nodes of the second set, and determining a path across the adapted computation graph via one replica node of the first set and one replica node of the second set based on the performance values.

Abstract: A line-of-sight detection apparatus includes a first direction determining section that determines a first direction that is a direction of a line of sight of a first eye of a subject; a second direction determining section that determines a second direction that is a direction of a line of sight of a second eye of the subject; an assuming section that assumes a gaze direction of the subject based on at least one of (i) a manipulation by the subject of a device provided with a line-of-sight measurement apparatus that measures a line of sight of the subject, (ii) a state of the device, and (iii) an orientation of a face of the subject; and a first judging section that compares the assumed gaze direction, the first direction, and the second direction, and judges which of the first eye and the second eye is a dominant eye.

Abstract: A method for training a machine learning model, including acquiring an initial machine learning model, updating features of the initial machine learning model, updating dimension of the initial machine learning model based on the updated features of the initial machine learning model and one or more latency hysteresis points obtained based on a hardware profile of an accelerator configured to perform machine learning operations, and generating a final machine learning model based on the updated dimensions.

Abstract: A system for flux residue detection is provided. The system includes a flux heater, where the flux heater controls a temperature of a flux spray applied to a printed circuit board, and an infrared camera, wherein the infrared camera provides a thermal image of the flux on the printed circuit board. A method, a computer system, and a computer program product for flux residue detection is provided, including setting flux application parameters, applying flux to a printed circuit board, and capturing an infrared image of the flux applied to the printed circuit board. A method, a computer system, and a computer program product for flux residue detection is provided, including setting flux application parameters, applying flux to a printed circuit board, capturing an infrared image of the flux applied to the printed circuit board, and determining there is excess flux residue on the printed circuit board.

Abstract: According to some embodiments, a socket for an electronic device includes a housing and pins connected to the housing. The housing includes a base extending laterally and having an inner face and an outer face; a riser connected to the base and extending away from the outer face; a wall extending laterally, connected to the riser, and having an exterior face and an interior face that faces the outer face of the base; mounting ports extending through the base from the inner face to the outer face; and exit ports extending through the wall from the interior face to the exterior face. Each pin includes a portion extending at least partially though one mounting port; a portion extending between the base and the wall; and a portion extending through one exit port.

Abstract: A line-of-sight detection apparatus includes a first direction determining section that determines a first direction that is a direction of a line of sight of a first eye of a subject; a second direction determining section that determines a second direction that is a direction of a line of sight of a second eye of the subject; an assuming section that assumes a gaze direction of the subject based on at least one of (i) a manipulation by the subject of a device provided with a line-of-sight measurement apparatus that measures a line of sight of the subject, (ii) a state of the device, and (iii) an orientation of a face of the subject; and a first judging section that compares the assumed gaze direction, the first direction, and the second direction, and judges which of the first eye and the second eye is a dominant eye.

Abstract: A disc-type speed regulation magnetic coupler based on bevel gear drive is provided, consisting of a driving disc assembly and a driven disc assembly, wherein a speed regulation device is mounted on the driving disc assembly.

Abstract: A method for quantizing a machine learning model during an inference phase, including determining a normalization factor using a set of floating-point values and a damped value of a damped value sequence; and assigning a quantized value for each floating-point value of the set of floating-point values based on the damped value sequence and the normalization factor.