Abstract: Logic may quantize a primary neural network. Logic may generate, by a secondary neural network logic circuitry for a primary neural network logic circuitry, quantization parameters. The primary neural network logic circuitry may comprise a primary neural network with multiple layers trainable with an objective function. Each of the multiple layers of the primary neural network may comprise multiple tensors. The secondary neural network logic circuitry may comprise one or more secondary neural networks trainable with the objective function to output the quantization parameters to the tensors.

Abstract: Described herein are techniques for generating a model based on input. In an example, a first model can be generated based on decomposing a rating matrix into a product of two matrices U and V, where U represents correlations between users and a plurality of factors and V represents correlations between items and the plurality of factors. At least some of the users and items can be grouped into groups according to the correlations. Input on one or more of the groups can be received. A second model can be generated based on the input on the one or more of the groups.

Abstract: Logic may quantize a primary neural network. Logic may generate, by a secondary neural network logic circuitry for a primary neural network logic circuitry, quantization parameters. The primary neural network logic circuitry may comprise a primary neural network with multiple layers trainable with an objective function. Each of the multiple layers of the primary neural network may comprise multiple tensors. The secondary neural network logic circuitry may comprise one or more secondary neural networks trainable with the objective function to output the quantization parameters to the tensors.

Abstract: Described herein are techniques for generating a model based on input. In an example, a first model can be generated based on decomposing a rating matrix into a product of two matrices U and V, where U represents correlations between users and a plurality of factors and V represents correlations between items and the plurality of factors. At least some of the users and items can be grouped into groups according to the correlations. Input on one or more of the groups can be received. A second model can be generated based on the input on the one or more of the groups.

Abstract: Disclosed herein are a system, non-transitory computer readable medium, and method for responding to a query having a plurality of input objects. A subgraph based on a main graph of objects is used to generate a list of objects associating the input objects.

Abstract: A system (100) can include a broker (110) to process a plurality of job requests (120) and automatically query for response parameters from a plurality of service providers (140) based on the plurality of job requests (120). An assignment function (150) can assign a job (130) associated with the plurality of job requests (120) to a service provider of the plurality of service providers (140) based on the received response parameters from the plurality of service providers (140) and based on balancing competing production interests across the plurality of service providers (140).

Abstract: Systems and methods for prioritizing print jobs of different families within a print job batch are provided. Such a system may include, for example, an input/output port and a processor. The input/output port may output a print job batch including at least one print job of a first family and at least one print job of a second family. The processor configured may determine the order of priority of the print job batch based at least in part on a first trend of expected differences in setup times between print machines when the first family is prioritized before the second family and a second trend when the second family is prioritized before the first family.

Abstract: An image registration method to register a target image with a reference image is provided, including to determine a target set of features present in the target image, to determine a reference set of features present in the reference image, to generate respective signatures for each feature in the target and reference sets, to match features from the target set to corresponding features in the reference set using the signatures, to generate respective transformations to map pairs of features in the target set to corresponding pairs of features in the reference set, and determine a similarity transformation for the target image using a measure of the accuracy of the transformations.

Abstract: Systems and methods are provided for scheduling print jobs in a print service provider (PSP). In particular, embodiments include accessing a first set of data relating to processing times for a plurality of machines of a print service provider (PSP). The processing times relate to specific print jobs or types of print jobs sharing print job characteristics. In addition, embodiments include accessing a second set of data relating to setup times for the plurality of machines of the PSP. The setup times relate to specific sets of two print jobs or sets of two types of print jobs sharing print job characteristics. Further, embodiments include determining an order of processing for a plurality of print jobs based on the first and second sets of data.

Abstract: Disclosed herein are a system, non-transitory computer readable medium, and method for responding to a query having a plurality of input objects. A subgraph based on a main graph of objects is used to generate a list of objects associating the input objects.

Abstract: A method and apparatus (70) is provided for estimating blur degradation of an image (75) that includes a specular highlight. A specular highlight in the image is first identified (77), for example with user assistance. A blur kernel is then derived by extracting (78A) the identified specular highlight as foreground from the image (75) and using the extracted foreground as the blur kernel (78C). The image (75) can then be deblurred by deconvolution (79) with the derived blur kernel.

Abstract: Systems and methods for prioritizing print jobs of different families within a print job batch are provided, Such a system may include, for example, an input/output port and a processor. The input/output port may output a print job batch including at least one print job of a first family and at least one print job of a second family. The processor configured may determine the order of priority of the print job batch based at least in part on a first trend of expected differences in setup times between print machines when the first family is prioritized before the second family and a second trend when the second family is prioritized before the first family.

Abstract: An image registration method to register a target image with a reference image is provided, including to determine a target set of features present in the target image, to determine a reference set of features present in the reference image, to generate respective signatures for each feature in the target and reference sets, to match features from the target set to corresponding features in the reference set using the signatures, to generate respective transformations to map pairs of features in the target set to corresponding pairs of features in the reference set, and determine a similarity transformation for the target image using a measure of the accuracy of the transformations.

Abstract: A method for determining with a physical image processing device a visual balance of an image includes assigning a visual weight point to each of a plurality of visual elements within the image with the image processing device, each visual weight point having a weight value based on visual properties associated with the visual element, and determining the visual balance of the image with the image processing device by measuring a vector value at a center of the composition, the vector value being based on a distance of each visual weight point from the center and the weight value associated with each visual weight point.

Abstract: A method for configuration policy extraction for an organization having a plurality of composite configuration items may include calculating distances in a configuration space between the composite configuration items. The method may also include clustering the composite configuration items into one or more dusters based on the calculated distances. The method may further include identifying configuration patterns in one or more of the clusters, and extracting at least one configuration policy based on the identified configuration patterns. A non-transitory computer readable medium and a system for configuration policy extraction for an organization having a plurality of composite configuration items are also disclosed.

Abstract: A method for online planning of a workflow for a job of processing an article in a plant in which other articles are currently being processed, may include, for each stage of the processing, assigning a machine cost value to each machine of the plant that is capable of executing that stage, the machine cost value being an exponential function of a current congestion of that machine. The method may also include constructing a plurality of workflow routes, each workflow route including a series of selected machines such that each selected machine of the series is capable of executing a different stage of the processing,. The method of may further include calculating for each workflow route of the plurality of workflow routes a route cost function that is based on the machine cost functions of the selected machines of that workflow route.

Abstract: A project management system (10) and method (250) are included. The project management system (10) includes a production database (14) in memory (15) to store project data (20). The project data (20) can include workflow resource data (16) describing workflow resources (54, 56) and feedback data (17) obtained for each workflow step (52) of a plurality of projects (18) of a project type (152). The project management system (10) also includes a processor (27) to access the memory (15) and to execute computer readable instructions including a production learning module (26) to analyze the workflow resource data (16) and the feedback data (17) to generate predictive project data (12). The predictive project data (12) can describe a predicted workflow (154) for a given project (18) of the project type (152) based on the workflow resources (54, 56).

Abstract: Systems and methods are provided for scheduling print jobs in a print service provider (PSP). In particular, embodiments include accessing a first set of data relating to processing times for a plurality of machines of a print service provider (PSP). The processing times relate to specific print jobs or types of print jobs sharing print job characteristics. In addition, embodiments include accessing a second set of data relating to setup times for the plurality of machines of the PSP. The setup times relate to specific sets of two print jobs or sets of two types of print jobs sharing print job characteristics. Further, embodiments include determining an order of processing for a plurality of print jobs based on the first and second sets of data.

Abstract: A method of reducing blurring in an image of size greater than M columns by N rows of pixels, comprises deriving a blur kernel k representing the blur in the image, and deriving an inverse blur kernel k?1. The inverse blur kernel is given by (I) where h(m) is the sum of the first m terms of the series (II) ? is the Dirac delta, m is greater than 1, and h(m) is a two dimensional matrix of size M×N. The two dimensional matrix h(m) is convolved with the image over the whole image in the image pixel domain to produce an image with reduced blur. The method may be applied to a video sequence allowing the sequence of images to be deblurred in real time.

Abstract: Automated imposition wherein a print job comprises multiple documents, and the documents comprise pages having different dimensions. Pages of different dimensions of the same document may be imposed on a single sheet, and pages of equal dimensions may be lined up in a layer across the sheet, forming a cut line along the layer and across the sheet.