Abstract: A system for classifying a target image with segments having attributes is provided. The system generates a graph for the target image that includes vertices representing segments of the image and edges representing relationships between the connected vertices. For each vertex, the system generates a subgraph that includes the vertex as a home vertex and neighboring vertices representing segments of the target image within a neighborhood of the segment represented by the home vertex. The system applies an autoencoder to each subgraph to generate latent variables to represent the subgraph. The system applies a machine learning algorithm to a feature vector comprising a universal image representation of the target image that is derived from the generated latent variables of the subgraphs to generate a classification for the target image.

Abstract: An approach is provided for providing a lower-power perception architecture. The approach involves, for example, determining that a device is equipped with a first perception system and a second perception system. The second perception system operates in a lower-power consumption mode than the first perception system to process image data for image recognition. The approach also involves determining a battery level of the device. The approach further involves switching from the first perception system to the second perception system based on determining that the battery level is below a threshold battery level.

Abstract: A system for evaluating and facilitating customized source code based on the usability guidelines using a usability code pattern analysis is provided. The system includes a decompile module, a guideline loader module, an inspection module, a validation module, a recommendation module, and one or more databases. The system obtains the input package from the user computing device to generate customized the usability code pattern for the input package by decompiling, inspecting and validating the input package against a validation case based on the usability guidelines. The input package layout files decompiled in XML and JAR file formats. The evaluation of the usability guideline is based on existing usability guidelines. The validation module validates the usability of the input package at each instance periodically using validation test cases.

Abstract: Described herein is a system for rescoring automatic speech recognition hypotheses for conversational devices that have multi-turn dialogs with a user. The system leverages dialog context by incorporating data related to past user utterances and data related to the system generated response corresponding to the past user utterance. Incorporation of this data improves recognition of a particular user utterance within the dialog.

Abstract: A technique for executing commands for an accelerated processing device is provided. The technique includes obtaining an iteration number and predication data from metadata for an iterative indirect command buffer; for each iteration indicated by the iteration number, performing commands of the iterative indirect command buffer as specified by the predication data; and ending processing of the iterative indirect command buffer in response to processing a number of iterations equal to the iteration number.

Abstract: A processor includes a task scheduling unit and a compute unit coupled to the task scheduling unit. The task scheduling unit performs a task dependency assessment of a task dependency graph and task data requirements that correspond to each task of the plurality of tasks. Based on the task dependency assessment, the task scheduling unit schedules a first task of the plurality of tasks and a second proxy object of a plurality of proxy objects specified by the task data requirements such that a memory transfer of the second proxy object of the plurality of proxy objects occurs while the first task is being executed.

Abstract: Methods and systems are provided to generate an uncorrupted version of an image given an observed image that is a corrupted version of the image. In some embodiments, a corruption mimicking (“CM”) system iteratively trains a corruption mimicking network (“CMN”) to generate corrupted images given modeled images, updates latent vectors based on differences between the corrupted images and observed images, and applies a generator to the latent vectors to generate modeled images. The training, updating, and applying are performed until modeled images that are input to the CMN result in corrupted images that approximate the observed images. Because the CMN is trained to mimic the corruption of the observed images, the final modeled images represented the uncorrupted version of the observed images.

Abstract: A processor dynamically selects a render mode for each render pass of a frame based on the characteristics of the render pass. A software driver of the processor receives graphics operations from an application executing at the processor and converts the graphics operations into a command stream that is provided to the graphics pipeline. As the driver converts the graphics operations into the command stream, the driver analyzes each render pass of the frame to determine characteristics of the render passes, and selects a render mode for each render pass based on the characteristics of the render pass.

Abstract: System and methods for predicting future pest pressures are provided. A pest pressure prediction computing device includes a memory and a processor communicatively coupled to the memory. The processor is programmed to receive trap data for a plurality of pest traps in a geographic location, receive weather data for the geographic location, receive image data for the geographic location, identify at least one geospatial feature within or proximate to the geographic location, apply a machine learning algorithm to the trap data, the weather data, the image data, and the at least one identified geospatial feature to identify a correlation between pest pressure and the at least one geospatial feature, and generate predicted future pest pressures for the geographic location based at least on the identified correlation between pest pressure and the at least one geospatial feature.

Abstract: Systems and methods related to controlling clock signals for clocking shader engines modules (SEs) and non-shader-engine modules (nSEs) of a graphics processing unit (GPU) are provided. One or more dividers receive a clock signal CLK and output a clock signal CLKA to the SEs and output a clock signal CLKB to the nSEs. The frequencies of CLKA and CLKB are independently selected based on sets of performance counter data monitored at the SEs and nSEs, respectively. The clock signal frequency for either the SEs or the nSEs is reduced when the corresponding sets of performance counter data indicates a comparatively lower processing workload for the SEs or for the nSEs.

Abstract: Systems, methods, and computer-readable media are disclosed for parallel data pool processing and intelligent item selection. In one embodiment, an example method may include determining a first bid request comprising a first user identifier, determining a first set of product identifiers in a first user interaction history of the first user identifier, determining a second bid request comprising a second user identifier, and determining a second set of product identifiers in a second user interaction history of the second user identifier. Example methods may include determining estimated values for one or more product identifiers in the first set of product identifiers and the second set of product identifiers in parallel, and generating respective first and second responses to the first bid request and the second bid request using the estimated values.

Abstract: A variety of polyoxyalkylene coupled zwitterionic moieties are provided as well as surface active reactive polymers containing the polyoxyalkylene coupled zwitterionic moieties. When incorporated in coating systems, such surface active polymers show strong propensity to stratify during curing. The zwitterionic groups presented at the end of polyalkylene oxide chains can allow for effective exposure of the zwitterionic groups at the coating/water interface as the polyoxyalkylene side chains of the said SAP can further extend (to its radius of gyration) into the water phase. Additional features of the polyoxyalkylene coupled zwitterionic moieties can include a reactive end group (R) to allow covalent attachment of the moiety to a surface, a particle, a small molecule, or a polymer. Coating compositions and coated articles containing the polyoxyalkylene coupled zwitterionic moieties are also provided.

Abstract: A production cluster includes a first plurality of nodes and executes a workload, such that jobs associated with the executed workload are allocated, according to a first configuration, across the first plurality of nodes. A cluster monitor extracts production cluster information from the production cluster, monitors configuration information during execution of the workload, and transmits each to a cluster tuner. The cluster tuner includes a second plurality of nodes that is less than the first plurality of nodes of the production cluster. The cluster tuner receives the information and determines a first recommended configuration for the production cluster. The cluster tuner causes the test cluster to execute a simulated workload according to the first recommended configuration. In response to determining that the first recommended configuration results in a decrease in resource consumption, the cluster tuner causes the production cluster to operate according to the first recommended configuration.

Abstract: A control server controls a dual-arm robotic manipulator (DARM) for handling deformable objects in a stack. The control server receives a set of images of the stack captured by a set of image sensors, and determines a contour of the stack based the set of images. Based on the contour and historical data associated with the deformable objects in the stack, the control server determines a sequence of actions to be performed by the DARM for handling a first deformable object in the stack, and controls the DARM to handle the first deformable object by communicating a set of commands corresponding to each action in sequence of actions. The first deformable object is handled such that original form factors of the first deformable object and the remaining stack are maintained.

Abstract: Sidechain functionalized organosiloxane compounds are provided having a first end and a second end; a polysiloxane backbone; and a first plurality of sidechains covalently attached to the polysiloxane backbone and a second plurality of sidechains covalently attached to the polysiloxane backbone; wherein the first plurality of sidechains comprise polyalkylene glycol sidechains; wherein the first plurality of sidechains and the second plurality of sidechains comprise a tethered end covalently attached to the polysiloxane backbone and a free end opposite to the tethered end; and wherein the free end in one or both of the first plurality of sidechains and the second plurality of sidechains comprises a reactive end group. Compositions comprising the sidechain functionalized organosiloxane compounds are also provided, as well as coated articles. Sidechain functionalized lubricants are also provided that can be used with compositions and coated articles herein.

Abstract: A system includes reception of a request from a first application to create a virtual open-channel solid state drive associated with a first bandwidth and first capacity, association, in response to the request, of block addresses of a virtual address space of the first application with block addresses of one or more blocks of a first one of a first plurality of channels of a first open-channel solid state drive and with block addresses of one or more blocks of a second one of the first plurality of channels, reception, from the first application, of a first I/O call associated with one or more block addresses of the virtual address space, determination of block addresses of one or more blocks of the first one of the first plurality of channels which are associated with the one or more block addresses of the virtual address space, and execution of the first I/O call on the determined block addresses of one or more blocks of the first one of the first plurality of channels.

Abstract: Methods, systems, and computer program products for generating explanations for a semantic parser are provided herein. A computer-implemented method includes providing to a generative model (i) at least one query and (ii) a context of at least one dataset applicable to the at least one query, wherein the generative model generates a plurality of perturbations for the at least one input query based on the context; providing the plurality of perturbations as inputs to a context aware sequence-to-sequence model, thereby obtaining a plurality of outputs; and generating, for (i) an additional query provided as input to the context aware sequence-to-sequence model and (ii) a context applicable to the additional query, an explanation indicative of one or more parts of the additional query that contributes to an output corresponding to the additional query, based at least in part on the plurality of outputs corresponding to the perturbations.

Abstract: A method, apparatus and computer program product are provided for warping a perspective image into the ground plane using a homography transformation to estimate a bird's eye view in real time. Methods may include: receiving first sensor data from a first vehicle traveling along a road segment in an environment, where the first sensor data includes perspective image data of the environment, and where the first sensor data includes a location and a heading; retrieving a satellite image associated with the location and heading; applying a deep neural network to regress a bird's eye view image from the perspective image data; applying a Generative Adversarial Network (GAN) to the regressed bird's eye view image using the satellite image as a target of the GAN to obtain a stabilized bird's eye view image; and deriving values of a homography matrix between the sensor data and the established bird's eye view image.

Abstract: Methods described herein relate to identifying critical parameters of a localization framework that may require tuning for accuracy of the localization framework based on the data source. Methods may include: receiving a data set from a data source; comparing the data set against data stored in a database; identifying, based on the comparison, a subset of parameters of a localization framework for the data set from among a plurality of parameters of the localization framework; providing for tuning of the subset of parameters of the localization framework for the data set to generate a tuned subset of parameters; processing the data set from the data source using the localization framework including the tuned subset of parameters; and receiving an indication of a location from the localization framework of the data set within a mapped region.

Abstract: An endoscopic surgical clip applier (10) includes a handle assembly (100) configured to releasably engage at least two in different endoscopic assemblies (200, 300). The handle assembly (100) is configured to transition from a non-ratcheting use condition to a ratcheting use condition when an endoscopic assembly (200) configured for ratcheting use is engaged with the handle assembly (100). The handle assembly (100) is maintained in the non-ratcheting use condition when an endoscopic assembly (300) configured for non-ratcheting use is engaged with the handle assembly (100). Endoscopic assemblies (200, 300) for use with the handle assembly (100) are also provided.