Abstract: Methods and systems for solving a linear system include setting resistances in an array of settable electrical resistances in accordance with values of an input matrix. A series of input vectors is applied to the array as voltages to generate a series of respective output vectors. Each input vector in the series of vectors is updated based on comparison of the respective output vectors to a target vector. A solution of a linear system is determined that includes the input matrix based on the updated input vectors.

Abstract: Techniques are provided to implement hardware accelerated computing of eigenpairs of a matrix. For example, a system includes a processor, and a resistive processing unit coupled to the processor. The resistive processing unit includes an array of cells which include respective resistive devices, wherein at least a portion of the resistive devices are tunable to encode values of a given matrix which is storable in the array of cells. When the given matrix is stored in the array of cells, the processor is configured to determine an eigenvector of the stored matrix by executing a process which includes performing analog matrix-vector multiplication operations on the stored matrix to converge an initial vector to an estimate of the eigenvector of the stored matrix.

Abstract: Embodiments of the invention are directed to using a trained machine learning model to generate predicted circuit data for a circuit design, and computing an objective function using the predicted circuit data. Optimization of the objective function is performed to generate an optimal solution, and the optimal solution is mapped to the circuit design.

Abstract: Matrix inversion systems and methods are implemented using an analog resistive processing unit (RPU) array for hardware accelerated computing. A request is received from an application to compute an inverse matrix of a given matrix, and a matrix inversion process is performed in response to the received request. The matrix inversion process includes storing a first estimated inverse matrix of the given matrix in an array RPU cells, performing a first iterative process on the first estimated inverse matrix stored in the array of RPU cells to converge the first estimated inverse matrix to a second estimated inverse matrix of the given matrix, and reading the second estimated inverse matrix from the array of RPU cells upon completion of the first iterative process. An inverse matrix is returned to the application, wherein the returned inverse matrix is based, at least in part, on the second estimated inverse matrix.

Abstract: Methods and systems for solving a linear system include setting resistances in an array of settable electrical resistances in accordance with values of an input matrix. A series of input vectors is applied to the array as voltages to generate a series of respective output vectors. Each input vector in the series of vectors is updated based on comparison of the respective output vectors to a target vector. A solution of a linear system is determined that includes the input matrix based on the updated input vectors.

Abstract: A computer-implemented method for Eigenpair computation is provided. The method includes computing, her a hardware processor, an Eigenvector and respective Eigenvalues of the Eigenvector of a matrix by using a modified Stochastic Optimization process including performing a matrix vector product on a Resistive Processing Unit (RPU) crossbar array operatively coupled to the hardware processor and performing a scalar vector product on a digital device operatively coupled to the hardware processor and representing, for each of an Eigenpair, an initial guess for the Eigenvector and the respective Eigenvalues. The computing step includes storing the matrix in the RPU crossbar array.

Abstract: A computer-implemented method for Eigenpair computation is provided. The method includes computing an Eigenvector and respective Eigenvalues of the Eigenvector by using a Stochastic Optimization process. The computing step includes storing the matrix in a Resistive Processing Unit (RPU) crossbar array.

Abstract: A method for operating a teleconference includes receiving a first video and audio signal from a first teleconference participant and receiving a second video and audio signal from a second teleconference participant. The method further includes relaying the first video and audio signal to the second teleconference participant and relaying the second video and audio signal to the first teleconference participant. The method additionally includes analyzing the first video and audio signal using a plurality of behavior analytics to determine a level of participant engagement of the first teleconference participant. The method further includes determining that the first teleconference participant is not engaged when the determined level of participant engagement is below a predetermined threshold.

Abstract: A method for operating a teleconference includes receiving a first video and audio signal from a first teleconference participant and receiving a second video and audio signal from a second teleconference participant. The method further includes relaying the first video and audio signal to the second teleconference participant and relaying the second video and audio signal to the first teleconference participant. The method additionally includes analyzing the first video and audio signal using a plurality of behavior analytics to determine a level of participant engagement of the first teleconference participant. The method further includes determining that the first teleconference participant is not engaged when the determined level of participant engagement is below a predetermined threshold.

Abstract: A model is built of benefit of each of a plurality of computing tasks under uncertainty as a function of computing resources invested in each of the computing tasks, and a model of risk is built of each of the computing tasks under uncertainty as a function of the computing resources invested in each of the computing tasks. Risk of a task allocation is calculated with the risk model, and benefit of a task allocation is calculated with the benefit model. An allocation of the computing resources is found to increase the benefit and manage the risk. The allocation of computing resources is applied to the computing tasks.

Abstract: A printing system is disclosed. The printing system includes a halftone calibration system that receives one or more un-calibrated halftones, generates one or more calibrated halftones using an ink model from the one or more un-calibrated halftones, analyzes a printed calibration screen of the one or more calibrated halftones, and performs a halftone calibration.

Abstract: A method is disclosed. The method includes generating a halftone screen using a Direct Multi-bit Search Screen Algorithm (DMSSA) to optimize a halftone pattern at each gray level.

Abstract: A method is disclosed. The method includes applying a human visual system (HVS) model to a Continuous Tone Image (CTI) and a initial Half Tone Image (HTI) to generate a perceived CTI and a perceived HTI and computing a change in pixel error for a first pixel by toggling the first pixel with all the possible output states and swapping the first pixel with all neighbor pixels.

Abstract: The present disclosure relates generally to the field of distributed charging of electrical assets. In various examples, distributed charging of electrical assets may be implemented in the form of systems, methods and/or algorithms.

Abstract: A method is disclosed. The method includes estimating a quantity of toner to be used to print a job at a printer by calculating a buildup of toner at edges of data on each page of the print job.

Abstract: A method is disclosed. The method includes generating a Continuous Tone Image (CTI) with all pixel values same as the first gray level and an initial Half Tone Image (HTI) with all pixel values equal to minimum absorptance level, computing a change in pixel error by toggling with all the possible output states and swapping with all neighbor pixels only if the stacking constraint is satisfied, updating the HTI with the maximum error decrease operation and continue to next pixel location till the end criteria is met. Once the end criteria is met, the updated HTI is saved as a final halftone screen for that gray level and copied as the initial HTI for the next gray level along with CTI pixel values updated to the next gray level till the final gray value is reached.

Abstract: A method is disclosed. The method includes applying a human visual system (HVS) model to a Continuous Tone Image (CTI) and a initial Half Tone Image (HTI) to generate a perceived CTI and a perceived HTI and computing a change in pixel error for a first pixel by toggling the first pixel with all the possible output states and swapping the first pixel with all neighbor pixels.

Abstract: A structure and method for temperature control includes determining a schedule for a climate control device needed for an inside temperature to reach a desired temperature, determining a perceptual temperature factor based on at least the schedule and the inside temperature, adjusting the desired temperature based on the perceptual temperature factor, and after the adjusting the desired temperature, repeating the determining the schedule.

Abstract: A method is disclosed. The method includes generating a set of points via energy minimization to implement halftone seed pattern.

Abstract: A method is disclosed. The method includes generating a Continuous Tone Image (CTI) with all pixel values same as a first gray level, generating an initial Half Tone Image (HTI) with all pixel values equal to minimum absorptance level and computing a change in pixel error for a first pixel. The change in pixel error is computed by identifying a first pixel indicated in a valid pixel map, toggling the first pixel with all the possible output states and swapping the first pixel with all neighbor pixels only if the stacking constraint is satisfied, updating the HTI with the maximum error decrease operation and continue to next pixel location till the end criteria is met.