Abstract: Methods for protecting software licensing information via a trusted platform module (TPM) are performed by systems and devices. When a licensing server is unreachable, a license is generated for a software application by a licensing manager. The license is generated via a secure register of the TPM using an asymmetric key, specific to the software application and policy-tied to the secure register, to generate a signature of a hashed license file for the software application. The asymmetric key is stored, mapped to the license file, and used for subsequent license validation. A licensing manager validation command is provided to validate the license using the key, as applied to the hash, to verify the signature and checking validity of the time stamp. Time stamp expiration or alteration of the license are determined to provoke invalidation indications for the validating application.

Abstract: Apparatus and methods are disclosed for using machine learning models with private and public domains. Operations can be applied to transform input to a machine learning model in a private domain that is kept secret or otherwise made unavailable to third parties. In one example of the disclosed technology, a method includes applying a private transform to produce transformed input, providing the transformed input to a machine learning model that was trained using a training set modified by the private transform, and generating inferences with the machine learning model using the transformed input. Examples of suitable transforms that can be employed include matrix multiplication, time or spatial domain to frequency domains, and partitioning a neural network model such that an input and at least one hidden layer form part of the private domain, while the remaining layers form part of the public domain.

Abstract: A neural architecture search (NAS) system generates a machine-trained model that satisfies specified real-time latency objectives by selecting among a collection of layer-wise sparse candidate models. In operation, the NAS system selects a parent model from among the candidate models. The NAS system then identifies a particular layer of the parent model, and then determines how the layer is to be mutated, to yield a child model. The NAS system calculates a reward score for the child model based on its latency and accuracy. The NAS system then uses reinforcement learning to update the trainable logic used to perform the mutating based on the reward score. The NAS system repeats the above process a plurality of times. An online application system can use the machine-trained model eventually produced by the NAS system to deliver real-time responses to user queries.

Abstract: Aspects of the present disclosure relate to generating an engagement model to predict actions that may have a high probability of maintaining user engagement in-application or causing a user to reengage with the application. To generate the engagement model, an approach has been developed which incorporates features analysis of the application and application users. Users may be grouped based on similar features that are used to generate machine learning engagement models. The output of an engagement model may be a prediction on whether a user will continue to engage with an application. The prediction may be provided to a reengagement model which may output prompts to help increase user engagement with the application. The prompts may be based on an understanding of application users and their preferences.

Abstract: A computer-implemented technique is described herein for providing assistance to a user in performing various computer-related tasks. The technique relies on a state machine system that transitions among plural modes based on mode-specific cues provided by a pattern-completion engine. The pattern-completion engine, in turn, is induced to generate these cues based on initial context information provided to a context store of the state machine system. Among other information, the initial context information provides example dialogues that are annotated with mode-specific cues. Throughout its operation, the technique updates context information provided in the context store. The plural modes can include at least a user mode, an answer mode, and a command mode. The technique also provides various mechanisms to ensure the privacy of sensitive-information items and to reduce the risk that commands will damage execution platforms.

Abstract: Video decoding innovations for multithreading implementations and graphics processor unit (“GPU”) implementations are described. For example, for multithreaded decoding, a decoder uses innovations in the areas of layered data structures, picture extent discovery, a picture command queue, and/or task scheduling for multithreading. Or, for a GPU implementation, a decoder uses innovations in the areas of inverse transforms, inverse quantization, fractional interpolation, intra prediction using waves, loop filtering using waves, memory usage and/or performance-adaptive loop filtering. Innovations are also described in the areas of error handling and recovery, determination of neighbor availability for operations such as context modeling and intra prediction, CABAC decoding, computation of collocated information for direct mode macroblocks in B slices, reduction of memory consumption, implementation of trick play modes, and picture dropping for quality adjustment.

Abstract: Systems and methods are provided for automatically determining an intent of a user based on an intent model to attach a file to a document, prompting the user to confirm the intent using a predetermined character in an inline nudge, generating and displaying an inline menu with an interactive list of ranked files as a suggestion for attachment. The disclosed technology uses the intent for specifying a scope of the inline search. The intent model for attaching content maintained by third-party applications uses a combination of an embeddings model and an N-gram model with limited seed queries and determines the intent based on intent scores associated with respective third-party applications. The present disclosure ranks respective candidate content based on a degree of relevance to the intent. The user selects one or more content from the list for attaching to the document.

Abstract: Embodiments relate to improving user experiences when executing binary code that has been translated from other binary code. Binary code (instructions) for a source instruction set architecture (ISA) cannot natively execute on a processor that implements a target ISA. The instructions in the source ISA are binary-translated to instructions in the target ISA and are executed on the processor. The overhead of performing binary translation and/or the overhead of executing binary-translated code are compensated for by increasing the speed at which the translated code is executed, relative to non-translated code. Translated code may be executed on hardware that has one or more power-performance parameters of the processor set to increase the performance of the processor with respect to the translated code. The increase in power-performance for translated code may be proportional to the degree of translation overhead.

Abstract: A controllable grounded response generation framework includes a machine learning model, a grounding interface, and a control interface. The machine learning model is trained to output computer-generated text based on input text. The grounding interface is useable by the machine learning model to access a grounding source including information related to the input text. The control interface is useable by the machine learning model to recognize a control signal. The machine learning model is configured to include information from the grounding source in the computer-generated text and focus the computer-generated text based on the control signal.

Abstract: A differential recurrent neural network (RNN) is described that handles dependencies that go arbitrarily far in time by allowing the network system to store states using recurrent loops without adversely affecting training. The differential RNN includes a state component for storing states, and a trainable transition and differential non-linearity component which includes a neural network. The trainable transition and differential non-linearity component takes as input, an output of the previous stored states from the state component along with an input vector, and produces positive and negative contribution vectors which are employed to produce a state contribution vector. The state contribution vector is input into the state component to create a set of current states. In one implementation, the current states are simply output.

Abstract: In some examples, techniques are provided for quick haptic feedback, without the use of a controller, which is local to individual, non-actuating keys, such as keys of a thin keyboard or keypad. The haptic feedback may be in the form of a simulated “key-click” feedback for an individual key that is pressed by a user such that the finger used to press the key feels the tactile sensation. The haptic feedback mimics the tactile sensation of a mechanical key (e.g., buckling spring, pop-dome key switch) to give a user the perception that they have actuated a mechanically movable key.

Abstract: The description relates to devices and air cooling of devices. One example can include a heat generating component positioned in a housing and a temperature-based gas separation assembly configured to receive ambient air and to separate the ambient air into warmer air that is directed outside the housing and cooler air that is directed inside the housing to cool the heat generating component.

Abstract: A system and method and for retrieving assets from a personalized asset library includes receiving a search query for searching for assets in one or more asset libraries, the one or more asset libraries including a personalized asset library; encoding the search query into embedding representations via a trained query representation machine-learning (ML) model; comparing, via a matching unit, the query embedding representations to a plurality of asset representations, each of the plurality of asset representations being a representation of one of the plurality of candidate assets; identifying, based on the comparison, at least one of the plurality of the candidate assets as a search result for the search query; and providing the identified plurality of candidate assets for display as the search result. The plurality of asset representations for the one or more assets in the personalized content library are generated automatically without human labeling.

Abstract: A method and system for intelligently organizing one or more groups of relevant files may include retrieving a user data signal including user-specific data, analyzing the user data signal to identify a parameter relating to file relevance, identifying one or more relevant files in a storage medium based on the parameter at least one of a user category property, a lifecycle stage property, a relevant activity property, or an activity level property of one or more files in the storage medium, organizing the one or more relevant file into the one or more groups of relevant files, and providing for display data relating to the one or more groups of relevant files.

Abstract: According to examples, an apparatus may include a processor and a memory on which is stored machine-readable instructions that may cause the processor to identify a container image group of a plurality of container image groups to which a subject container image corresponds, in which each of the plurality of container image groups is assigned a respective behavioral profile. The processor may also determine whether activities in the subject container image comply with corresponding activities identified in the behavioral profile of the identified container image group. Based on a determination that at least one activity in the subject container image fails to comply with a corresponding at least one activity identified in the behavioral profile of the identified container image group, the processor may determine that the subject container image includes an anomalous activity and output an alert indicating that the subject container image includes an anomalous activity.

Abstract: Examples are disclosed that relate to efficiently producing multiple laser beams of a harmonic frequency from a fundamental frequency beam. One example provides a laser system comprising a laser configured to output a fundamental frequency beam, a first harmonic-generation stage, and a second harmonic-generation stage. The first harmonic-generation stage is configured to receive an input of the fundamental frequency beam from the laser, and output from the laser system a first-stage harmonic frequency beam and a first-stage residual fundamental frequency beam. The second harmonic-generation stage is configured to receive an input of the first-stage residual fundamental frequency beam, and to output from the laser system a second-stage harmonic frequency beam.

Abstract: The description relates to cameras, and camera calibration for enhancing user experiences. One example can receive a first image of a user at a first location relative to a camera. The first image can include the user's upper body but does not include the user from head to toe. The example can receive a second image of the user at a second location relative to a camera. The second image can include the user's upper body but does not include the user from head to toe. The example can estimate a distance of the second location from the first location relative to the camera and calibrate a height and tilt angle of the camera from the first image, the second image, and the estimated distance and without a full body image of the user.

Abstract: Systems and methods for initiating an instant messaging chat session from an email thread are described. In examples, an email thread including at least one email is received and user identifiers form the at least one email are extracted. Presence information associated with each user identifier of the plurality of user identifiers is obtained and then ordered. The ordered plurality of user identifiers together with their presence information are displayed in a user interface window. A determination to display a user control associated with an instant messaging capability is based on the presence information associated with at least one user identifier of the plurality of user identifiers. Upon receiving an indication that the user control associated with the instant messaging chat capability is selected, an instant messaging chat session is initiated.

Abstract: A method for virtually representing human body poses includes receiving positioning data detailing parameters of one or more body parts of a human user based at least in part on input from one or more sensors. One or more mapping constraints are maintained that relate a model articulated representation to a target articulated representation. A model pose of the model articulated representation and a target pose of the target articulated representation are concurrently estimated based at least in part on the positioning data and the one or more mapping constraints. The previously-trained pose optimization machine is trained with training positioning data having ground truth labels for the model articulated representation. The target articulated representation is output for display with the target pose as a virtual representation of the human user.

Abstract: A system includes: a processor; and memory including instructions that, when executed by the processor, cause the processor to: receive personalization profile parameters from a user of a relevant resource device; calculate a representative utilization of the relevant resource device based on the personalization profile parameters; and generate the recommendation based on the representative utilization and the personalization profile parameters.

Abstract: Aspects of the present disclosure relate to assisting a requestor to manage activities a cross a plurality of diverse actors. In examples, a system is provided that includes at least one processor, and memory storing instructions that, when executed by the at least one processor, causes the system to perform a set of operations. The set of operations include receiving a request for a task to be completed, from the requestor, receiving actor context data, recording an assignment of the task to an actor, based on the actor context data, generating a communication to request that the actor complete the assigned task, and sending the communication to the actor.

Abstract: Examples are disclosed herein that relate to eye imaging on a near-eye system using an eye-imaging camera that includes an array of lenses. One example provides a near-eye system, comprising an eye-imaging camera comprising an image sensor, and an array of lenses, each lens of the array of lenses configured to focus an image of an eye onto a different area of the image sensor than each other lens of the array of lenses.

Abstract: Systems, methods, and a computer-readable medium are provided for matching textless elements to texted elements in video content. A video processing system including a textless matching system may divide a video into shots, identify shots having similar durations, identify sequences of shots having similar durations, and compare image content in representative frames of the sequences to determine whether the sequences match. When the sequences are determined to match, the sequences may be paired, wherein the first sequence may include shots with overlaid text and the second sequence may include textless version of corresponding texted shots included in the first sequence. In some examples, the video processing system may further replace the determined corresponding texted shots.

Abstract: A method is presented for operating a machine learning model including one or more mixture of experts layers. The method comprises receiving one or more input data shards at a routing gate network for a mixture of experts layer comprising a plurality of neural network experts. One or more neural network experts in the mixture of experts layer is designated layer to evaluate each input data shard. For each designated neural network expert, a weight matrix is retrieved having a predetermined sparsity to generate a sparsified designated neural network expert. Each input data shard is evaluated with a respective sparsified designated neural network expert.

Abstract: Methods and systems for applying gaze adjustment techniques to participants in a video conference are disclosed. Some examples may include: receiving, at computing system, image adjustment information associated with a video stream including images of a first participant, identifying, for a display layout of a communication application, a location displaying the images of the first participant, determining, based on the received image adjustment information, a location displaying images of a second participant for the display layout, the received image adjustment information indicating that an eye gaze of the first participant being directed toward the second participant, computing an eye gaze direction of the first participant based on the location displaying images of the second participant, generating gaze-adjusted images based on the desired eye gaze direction of the first participant and replacing the images within the video stream with the gaze-adjusted images.

Abstract: An authentication assay using embedded deoxyribonucleic acid (DNA) taggants includes a substrate and a sample of an authenticity label collected from a product. The substrate has a plurality of assay locations, each of which includes a reporter oligonucleotide bound to the substrate. The reporter oligonucleotide includes a first region with a single-stranded toehold sequence, a second region with a universal sequence, and a third region with a unique sequence, the second and third regions being prehybridized with a complementary strand. The sample includes at least one fluorophore-labeled DNA taggant complementary to the first and second regions of the reporter oligonucleotide. Incubation of the substrate with the sample results in a toehold-mediated DNA strand displacement reaction that exchanges the complementary strand for the fluorophore-labeled DNA taggant. Excitation of the fluorophore molecule attached to the DNA taggant produces a pattern of light emitted at one or more assay locations.

Abstract: Examples are disclosed that relate to safely accessing sensitive content in non-safe environments. One example provides a host computing device comprising an output device, a processor, and memory comprising instructions executable by the processor. The instructions are executable to receive a request to present a content item, access security information for the content item, and determine a current environment of the host computing device. The instructions are further executable to, when it is determined from the security information that the content item is a sensitive content item and that the current environment is not a safe environment for the content item, prevent presentation of the content item by the output device and send the content item to a private presentation device.

Abstract: A method is presented for training a neural network. For a weight matrix having integer dimensions M1 in a first dimension and an integer dimension M2 in a second dimension, a first balanced sparsity mask is generated that is an N1 of M1 mask in the first dimension. The first balanced sparsity mask is applied to the weight matrix during inference. A second balanced sparsity mask is generated for a transpose of the weight matrix. The second balanced sparsity mask is an N2 of M2 mask in the second dimension. The second balanced sparsity mask is applied to the transpose of the weight matrix during backpropagation.

Abstract: Examples are disclosed that relate to using an array of hot mirrors in an eye-imaging system. One example provides a head-mounted display system, comprising a frame, an eye-imaging camera supported on the frame, a switchable hot mirror array comprising a plurality of switchable hot mirrors configured to direct light reflecting from an eye toward the eye-imaging camera, and a controller configured to control switching of a reflectivity of each of the plurality of switchable hot mirrors.

Abstract: A dynamic offloading system is provided, which monitors resource demand by one or more applications executing on an on-prem server and supply of curated cloud space on one or more registered cloud service providers to automatically create an instance and offload applications associated with spikes in the resource demand. The curated cloud space may be preconfigured for specific processing and/or more general processing. For instance, the curated cloud space may be preconfigured for offloading service applications associated with mobile traffic, which may include specific resource requirements, time or service constraints, provisioning, testing or validation. Additionally, the curated cloud space may be preconfigured for offloading websites or databases, which may have more generalized resource requirements, provisioning, testing or validation.

Abstract: An initial mesh is received comprising a hand of a subject. The initial mesh includes a plurality of vertices. A smoothed mesh is generated, and a discrete curvature of the smoothed mesh is determined for each vertex. One or more candidate finger vertices are identified based upon a determination that the discrete curvature for each of the one or more candidate vertices is greater than or equal to a threshold curvature. One or more seed vertices are identified from among the one or more candidate finger vertices based upon a determination that the discrete curvature for one or more other vertices within a neighborhood of each seed vertex is greater than or equal to the threshold curvature. Dilation is performed on the one or more seed vertices to grow one or more patches from the one or more seed vertices. The one or more patches are deprioritized for mesh simplification.

Abstract: Techniques for optically detecting a subject chemical species within an atmospheric environment are disclosed. Image data is obtained representing multispectral imagery of a geographic region captured through the atmospheric environment. The image data includes an array of band-specific intensity values for each of a plurality of spectral bands, including a sample spectral band having increased sensitivity to the subject chemical species as compared to a plurality of reference spectral bands. A background reflectance map is generated that includes an array of inter-band intensity values in which each inter-band intensity value represents a filtered combination of band-specific intensity values of albedo-normalized arrays for a grouped subset of the plurality of reference spectral bands. The albedo-normalized array of band-specific intensity values for the sample spectral band is compared to the background reflectance map to obtain an index array of intensity variance values for the subject chemical species.

Abstract: A computing system is configured to implement a deep neural network comprising an input layer for receiving inputs applied to the deep neural network, an output layer for outputting inferences based on the received inputs, and a plurality of hidden layers interposed between the input layer and the output layer. A plurality of nodes selectively operate on the inputs to generate and cause outputting of the inferences, wherein operation of the nodes is controlled based on parameters of the deep neural network. A sparsity controller is configured to selectively apply a plurality of different sparsity states to control parameter density of the deep neural network. A quantization controller is configured to selectively quantize the parameters of the deep neural network in a manner that is sparsity-dependent, such that quantization applied to each parameter is based on which of the plurality of different sparsity states applies to the parameter.

Abstract: In examples, a saliency metric may be determined for an instance of content and/or a location of a digital environment. Accordingly, a set of candidate content and/or locations may be ranked according to associated saliency metrics, such that content and/or an associated location with which to adapt the digital environment for a given user may be determined from a set of candidates. For example, the digital environment may be adapted to present a two-dimensional or a three-dimensional asset to a user. As another example, a game mechanic of the digital environment may be altered. In examples, content from another digital environment may be identified and used to adapt the digital environment, thereby incorporating external content. Thus, a saliency metric associated with a location or an instance of content may be used to programmatically generate a relative or absolute metric with which to evaluate and adapt aspects of the digital environment.

Abstract: A method for performing conditional copying of a data object in a data environment to prevent a copying operation failure includes receiving a request to copy the data object to a destination source, the request including an identification of a first source data object, a second source data object and indication of an order of preference between the first data object and the second data object for copying the data object; determining based on the order that data object should be copied from the first source data object; examining a first source indicator to determine if the first source data object is available for copying; based on the determination, copying the data object from the first source data object to the destination source, when the first source data object is available and copying the copying the data object from the second source data object to the destination source, when the first source data object is not available; and creating an indication of successful copying of the data object to the des

Abstract: A method for signal request caching is described. Signal requests are received at a signal processor from a plurality of computing devices. The received signal requests are routed to a signal data store. An ingestion rate of the received signal requests is monitored by the signal processor. When the ingestion rate meets a signal request rate threshold of the signal data store, overflow signal requests of the received signal requests are automatically routed to an intermediate cache instead of the signal data store. The overflow signal requests within the intermediate cache are aggregated into one or more signal packages, each of the one or more signal packages containing a plurality of overflow signal requests. The one or more signal packages are stored at the signal data store.

Abstract: Systems and methods for providing enterprise-level application content customization are described herein. A method includes executing an enterprise application (from a suite of enterprise applications that are utilized by the enterprise) on a remote computing system operated by an enterprise administrator. The method includes surfacing a content customization UI on a display device of the remote computing system during execution of the enterprise application. The content customization UI includes UI elements that enable the specification of parameters for providing enterprise-specific customized content during execution of enterprise application(s) from the suite of enterprise applications on remote computing system(s) operated by enterprise user(s). The method also includes receiving, via the content customization UI, user input including the specification of parameters and generating the customized content based on the specified parameters.

Abstract: Systems and methods directed to returning personalized image-based search results are described. In examples, a query including an image may be received, and a personalized item embedding may be generated based on the image and user profile information associated with a user. Further, a plurality of candidate images may be obtained based on the personalized item embedding. The candidate images may then be ranked according to a predicted level of user engagement for a user, and then diversified to ensure visual diversity among the ranked images. A portion of the diversified images may then be returned in response to an image-based search.

Abstract: This document relates to compilation of source code into services. One example method involves receiving input source code, identifying data dependencies in the input source code, and identifying immutability points in the input source code based at least on the data dependencies. The example method also involves converting at least some of the input source code occurring after the immutability points to one or more service modules.

Abstract: A system and method for automatically identifying an operating procedure for resolving a customer support request includes receiving a customer support request for resolving an issue, encoding the issue into one or more text encoding representations, providing the one or more text encoding representations as a first input to a matching and selection unit, providing operating procedure encodings for a plurality of operating procedures as a second input to the matching and selection unit, comparing, by the matching and selection unit, the one or more text encoding representations to the operating procedure encodings to identify one or more operating procedures for resolving the issue, and providing the one or more operating procedures as recommendations for resolving the issue, wherein at least one of the one or more text encoding representations and the operating procedure encodings are generated by utilizing a geometric progressing natural language processing (NLP) algorithm.

Abstract: Examples are disclosed that relate to a battery and a functional module on a detachable module. One example provides a wearable device comprising a frame configured to support the wearable device on a user, internal charge storage located within the frame, a module interface located on the frame, and an electrical connector located within the module interface to electrically connect to a detachable module positioned in the module interface such that that detachable module is replaceable while being worn without powering down the wearable device by operating the wearable device using the internal charge storage.

Abstract: Implementations of the subject matter described herein provide a solution for rate control based on reinforcement learning. In this solution, an encoding state of a video encoder is determined, the encoding state being associated with encoding of a first video unit by the video encoder. An encoding parameter associated with rate control in the video encoder is determined by a reinforcement learning model and based on the encoding state of the video encoder. A second video unit different from the first video unit is encoded based on the encoding parameter. In this way, it is possible to achieve a better quality of experience (QOE) for real time communication with computation overhead being reduced.

Abstract: A method for operating a machine learning model is presented. The machine learning model includes a plurality of sequential transformer blocks. The method comprises receiving input data at a transformer block and processing the input data via a mixture of experts layer. At an auxiliary classifier, a measure of perplexity of the processed input data is determined. Based on the determined measure of perplexity, one or more experts in a downstream transformer block that will subsequently process the input data are indicated. Weight matrices are then fetched for the indicated one or more experts.

Abstract: Examples are disclosed that relate to backlight modules, displays including a backlight module, and methods for assembling a backlight module. In one example, a backlight module for a display comprises light sources affixed to a printed circuit and a light guide plate. An adhesive affixes the printed circuit to the light guide plate. The light guide plate comprises a body and a plurality of projections extending from the body, with the plurality of projections retaining two or more of the light sources between the projections and the body of the light guide plate.

Abstract: A computing system includes an illumination light source configured to emit illumination light into an external environment and an orientation sensor configured to estimate an orientation of the illumination light source relative to the external environment. The computing system includes a logic subsystem and a storage subsystem holding instructions executable by the logic subsystem to define a light restriction zone within the external environment. Based at least in part on the orientation of the illumination light source, the illumination light source is dynamically controlled to direct the illumination light toward at least a portion of the external environment outside the light restriction zone, while mitigating emission of the illumination light into the light restriction zone.

Abstract: Aspects of the present disclosure relate to multi-user, multi-device gaze tracking. In examples, a system includes at least one processor, and memory storing instructions that, when executed by the at least one processor, causes the system to perform a set of operations. The set of operations include identifying a plurality of computing devices, and identifying one or more users. The set of operations may further include receiving gaze input data and load data, from two or more of the plurality of computing devices. The set of operations may further include performing load balancing between the plurality of devices, wherein the load balancing comprises assigning one or more tasks from a first of the plurality of computing devices to a second of the plurality of computing devices based upon the gaze input data.

Abstract: A system and method to allow an authorized searcher to conduct a search of a current primary version of a document being developed in an application as well as versions of the document which were used in the development of the current primary version. In an exemplary system, instructions cause a processor to grant a search request to search, via a search index in a cloud storage, stored selected versions of the document. The stored selected versions of the document are historical versions of the current primary version of the document which has been selected from among the stored selected versions to be accessible, via the search index, to other searchers having a lower access authorization than the predetermined access authorization. The authorized searcher is provided with a capability to toggle between searching only the primary version of the document and searching the stored selected versions of the document.

Abstract: Systems and methods for reconfiguring application windows in a display. An example method includes displaying a first application window and a second application window; receiving a drag input for moving the first application window; based on the drag input entering an invocation region, displaying a layout menu with a plurality of display layouts, each of the display layouts including one or more snap zones; receiving a hover of the first application window over a particular snap zone of a particular display layout of the plurality of display layouts; based on the hover of the first application window over the particular snap zone, displaying a zone-indicator pane corresponding to the particular snap zone; receiving a drop input of the first application window over the particular snap zone; and in response to the drop input, resizing and repositioning the first application window according the particular snap zone.

Abstract: A computing device including a processor configured to receive an exact objective function over a state space. The processor may receive an approximated objective function that approximates the exact objective function. The processor may compute an estimated optimal state of the exact objective function. Computing the estimated optimal state may include, starting at an initial state, computing a preliminary estimated optimal state by performing a plurality of fast-step iterations of a Monte Carlo algorithm with respective fast-step acceptance probabilities determined based at least in part on the approximated objective function. Computing the estimated optimal state may further include performing a correction iteration that has a correction-step acceptance probability determined based at least in part on respective values of the approximated objective function and the exact objective function computed at the preliminary estimated optimal state. The processor may output the estimated optimal state.

Abstract: A computerized vehicle route optimization system is provided, including a processor configured to receive a graph of service location nodes and edges representing a travel cost metric between the service location nodes. The processor is further configured to, for each vehicle, determine a vehicle capacity, and instantiate a route data structure storing an ordered list of service location nodes, ordered by travel order. The processor is further configured to cluster the graph into node clusters such that a total of the service weighting values of all service location nodes in each node cluster is under the vehicle capacity. The processor is further configured to populate the ordered list of each route data structure with the service location nodes in a respective cluster, and optimize, via a hybrid reinforcement learning-annealing module, the ordered list of each route data structure to minimize a total travel cost metric of the plurality of vehicles.