Abstract: In one embodiment, a method for machine learning acceleration includes receiving instructions to perform convolution on an input tensor using a filter tensor, determining that the size of a first dimension of the input tensor is less than a processing capacity of each of multiple subarrays of computation units in a tensor processor, selecting a second dimension of the input tensor along which to perform the convolution, selecting, based on the second dimension, one or more dimensions of the filter tensor, generating (1) first instructions for reading, using vector read operations, activation elements in the input tensor organized such that elements with different values in the second dimension are stored contiguously in memory, and (2) second instructions for reading weights of the filter tensor along the selected one or more dimensions, and using the first and second instructions to provide the activation elements and the weights to the subarrays.

Abstract: In one embodiment, a method for machine learning acceleration includes receiving, by a shared controller of a tensor processor cluster that includes multiple tensor processors, a multi-cycle instruction, determining, based on the instruction, a sequence of vector operations to be executed by the tensor processors and address information usable to determine a respective spatial partition of an input tensor on which each tensor processor is to operate when performing each vector operation. The method also includes, for each vector operation in the sequence, generating, based on the address information, a common address offset, relative to a respective base address associated with each tensor processor, at which each tensor processor is to retrieve the respective spatial partition on which the tensor processor is to operate, multicasting the common address offset to the tensor processors, and controlling the tensor processors to execute the vector operation in parallel and in lock step.

Abstract: In one embodiment, a method includes accessing a video captured by cameras which is associated with a first framerate lower than a threshold framerate, for any two adjacent frames of the accessed video: generating a warped frame from the two adjacent frames based on an optical flow associated with the two adjacent frames, determining alignments for the two adjacent frames, respectively, fusing the determined alignments for the two adjacent frames, and generating a reconstructed frame based on the fused alignment, and reconstructing the accessed video based on the any two adjacent frames and their respective reconstructed frames, wherein the reconstructed video is associated with a second framerate higher than the threshold framerate.

Abstract: Disclosed herein is a method for using a neural network across multiple devices. The method can include receiving, by a first device configured with a first one or more layers of a neural network, input data for processing via the neural network implemented across the first device and a second device. The method can include outputting, by the first one or more layers of the neural network implemented on the first device, a data set that is reduced in size relative to the input data while identifying one or more features of the input data for processing by a second one or more layers of the neural network. The method can include communicating, by the first device, the data set to the second device for processing via the second one or more layers of the neural network implemented on the second device.

Abstract: A method of using computer-generated predicted image frames to create a high-dynamic-range (HDR) video is described. A method includes receiving first and second captured image frames via an image sensor. The first captured image frame represents a scene in the real-world at a first point in time and the second captured image frame represents the scene in the real-world at a second point in time that is after the first point in time. The method further includes in accordance with a determination that the first captured image frame and the second captured image frame will be used to produce an HDR video, generating a computer-generated predicted image frame representing the scene in the real-world at a time between the first point in time and the second point in time and fusing the second image frame with the computer-generated predicted image frame to generate an HDR frame for the HDR video.

Abstract: A method for providing performance assessment of terminal devices is provided. A user initiates, by way of a service application that runs on a user device of the user, a first request for obtaining risk scores or connectivity scores of the terminal devices. The first request may include terminal identifiers of specific terminal devices or information pertaining to a specific geographical area. The user device communicates the first request to a server. The server determines the risk scores or the connectivity scores based on the first request. The server transmits, to the user device, a first response that includes the risk scores or the connectivity scores. The user device displays the risk scores or the connectivity scores to the user based on the first response, thereby providing the performance assessment of the terminal devices.

Abstract: Described herein is a system and method for using object references as a data type. In response to a request for an object reference for an object by a consuming application, the object reference is generated by a source application. The object reference comprises a data structure comprising an activation uniform resource identifier for activating the referenced object, information for visually representing the object reference, and, optionally, metadata that describes the referenced object. The generated object reference is provided to an operating system component by the source application which provides the object reference to a consuming application. The consuming application can display information regard the object reference in accordance with the information for visually representing the object reference included in the object reference. The user can request reactivation of the object referenced by the object reference.

Abstract: According to one embodiment of the present disclosure, a device comprises a latching circuitry, where the latching circuitry comprises at least one correlated electron random access memory (CeRAM) element. The latching circuitry further comprises a control circuit coupled to the at least one CeRAM element. The control circuit is configured to receive at least one control signal. Based on the at least one control signal, perform at least one of storing data into the latching circuitry and outputting data from the latching circuitry.

Abstract: In one embodiment, a method for machine learning acceleration includes receiving, by a shared controller of a tensor processor cluster that includes multiple tensor processors, a multi-cycle instruction, determining, based on the instruction, a sequence of vector operations to be executed by the tensor processors and address information usable to determine a respective spatial partition of an input tensor on which each tensor processor is to operate when performing each vector operation. The method also includes, for each vector operation in the sequence, generating, based on the address information, a common address offset, relative to a respective base address associated with each tensor processor, at which each tensor processor is to retrieve the respective spatial partition on which the tensor processor is to operate, multicasting the common address offset to the tensor processors, and controlling the tensor processors to execute the vector operation in parallel and in lock step.

Abstract: Co-crystals of meloxicam co-formers can be prepared by co-crystallization from a polar solvent, such as aqueous dimethyl sulfoxide; or by slurry processes, such as with ethyl acetate. Such co-crystals have improved purities and are physically stable under storage for several months.

Abstract: An approach is provided for predicting an exception during a debugging of software code before the debugging encounters the exception. During a debugging of a line number L of the code and based on an exception being predicted to be encountered at a line number M, a warning is displayed that the exception is to be encountered at the line number M, which is within a range of line numbers L+1 through L+X, where L>0 and X>1. Using a fix written in response to the predicted exception, the software code is modified. During a debugging of the line number M of the code, the modified software code is executed to avoid the predicted exception.

Abstract: Disclosed herein includes a system, a method, and a device including shift circuitry and add circuitry for performing multiplication of a first value and a second value for a neural network. The first value has a predetermined format including a first bit, and two or more second bits to represent a value of zero or 2n where n is an integer greater than or equal to 0. The device shifts, when the two or more second bits represent the value of 2n, the second value by (n+1) bits via the shift circuitry to provide a first result, selectively outputs zero or the second value, based on a value of the first bit of the first value, to provide a second result, and adds the first result and the second results via the add circuitry to provide a result of the multiplication of the first and second values.

Abstract: Broadly speaking, embodiments of the present technique provide a neuron for a spiking neural network, where the neuron is formed of at least one Correlated Electron Random Access Memory (CeRAM) element or Correlated Electron Switch (CES) element.

Abstract: Disclosed herein includes a system, a method, and a device including shift circuitry and add circuitry for performing multiplication of a first value and a second value for a neural network. The first value has a predetermined format including a first bit, and two or more second bits to represent a value of zero or 2n where n is an integer greater than or equal to 0. The device shifts, when the two or more second bits represent the value of 2n, the second value by (n+1) bits via the shift circuitry to provide a first result, selectively outputs zero or the second value, based on a value of the first bit of the first value, to provide a second result, and adds the first result and the second results via the add circuitry to provide a result of the multiplication of the first and second values.

Abstract: Disclosed herein is a method for using a neural network across multiple devices. The method can include receiving, by a first device configured with a first one or more layers of a neural network, input data for processing via the neural network implemented across the first device and a second device. The method can include outputting, by the first one or more layers of the neural network implemented on the first device, a data set that is reduced in size relative to the input data while identifying one or more features of the input data for processing by a second one or more layers of the neural network. The method can include communicating, by the first device, the data set to the second device for processing via the second one or more layers of the neural network implemented on the second device.

Abstract: A method for providing performance assessment of terminal devices is provided. A user initiates, by way of a service application that runs on a user device of the user, a first request for obtaining risk scores or connectivity scores of the terminal devices. The first request may include terminal identifiers of specific terminal devices or information pertaining to a specific geographical area. The user device communicates the first request to a server. The server determines the risk scores or the connectivity scores based on the first request. The server transmits, to the user device, a first response that includes the risk scores or the connectivity scores. The user device displays the risk scores or the connectivity scores to the user based on the first response, thereby providing the performance assessment of the terminal devices.

Abstract: A method and apparatus is provided for wear leveling of a storage medium in an electronic device. Wear leveling is achieved by mapping each logical memory address to a corresponding physical memory address. The mapping information is consistent over an on-period of a power cycle, but changes from one power cycle to another. The mapping information, such as a key value for example, may be stored in non-volatile memory such as, for example, a correlated electron random switch (CES) storage element. The mapping may be obtained by manipulating bits of the logical address to obtain the physical address.

Abstract: A method and a system for processing transactions is provided. A terminal device executes a terminal action analysis on a transaction initiated at the terminal device by way of a transaction card. The terminal device compares a fraud count of the terminal device with a threshold fraud limit. If the fraud count exceeds the threshold fraud limit, the terminal device selects a first action from a set of actions for processing the transaction. When the first action is to authorize the transaction online, the terminal device transmits transaction details of the transaction to an acquirer server. The transaction details are indicative of a result of the terminal action analysis. The acquirer server generates an authorization request including a fraud indicator and updates the fraud indicator from a first value to a second value. The acquirer server communicates the authorization request, including the updated fraud indicator, to an issuer for authorization.

Abstract: The present disclosure provides novel crystalline sofosbuvir form-M3 and a process for the preparation of sofosbuvir form-M3. The crystalline sofosbuvir form-M3 disclosed herein may be useful in the formulation of pharmaceutical dosage forms.

Abstract: Described herein is a system and method for using object references as a data type. In response to a request for an object reference for an object by a consuming application, the object reference is generated by a source application. The object reference comprises a data structure comprising an activation uniform resource identifier for activating the referenced object, information for visually representing the object reference, and, optionally, metadata that describes the referenced object. The generated object reference is provided to an operating system component by the source application which provides the object reference to a consuming application. The consuming application can display information regard the object reference in accordance with the information for visually representing the object reference included in the object reference. The user can request reactivation of the object referenced by the object reference.