Abstract: A materialization configuration request is received via a programmatic interface from a client of a journal-based multi-data-store database. The request indicates a partitioning rule to be used to select, for respective writes indicated in committed transaction entries of a journal, the materialization node at which the writes are to be stored. A control plane component of the database verifies that a set of materialization nodes corresponding to the partitioning rule has been established, and initiates the propagation of writes from the journal to the materialization nodes by respective write appliers.

Abstract: A database management system receives a command defining a view of the database. The view definition is accepted without determining whether references to schema elements within the view definition are resolvable to existing elements of the database schema. A query of the view is received. In response to the query of the view, the database management system resolves references to schema elements in the view definition by determining whether the references correspond to data available for processing the query.

Abstract: A first computing device acquires video data representing a user performing an activity. The first device uses a first pose extraction algorithm to determine a pose of the user within a frame of video data. If the pose is determined to be potentially inaccurate, the user is prompted for authorization to send the frame of video data to a second computing device. If authorization is granted, the second computing device may use a different algorithm to determine a pose of the user and send data indicative of this pose to the first computing device to enable the first computing device to update a score or other output. The second computing device may also use the frame of video data as training data to retrain or modify the first pose extraction algorithm, and may send the modified algorithm to the first computing device for future use.

Abstract: A first configurable address decoder can be coupled between a source node and a first interconnect fabric, and a second address decoder can be coupled between the first interconnect fabric and a second interconnect fabric. The first address decoder can be configured with a first address mapping table that can map a first set of address ranges to a first set of target nodes connected to the first interconnect fabric. The second address decoder can be configured with a second address mapping table that can map a second set of address ranges to a second set of target nodes connected to the second interconnect fabric. The second address decoder can be part of the first set of target nodes. The first address decoder and the second address decoder can be configured or re-configured to determine different routes for a transaction from the source node to a target node in the second set of target nodes via the first and second interconnect fabrics.

Abstract: This disclosure describes systems and methods for using a primary device, communicatively coupled to a remote system, to configure or re-configure a secondary device in the same environment as the primary device. In some instances, the primary device may communicatively couple to the secondary device via a short-range wireless connection and to the remote system via a wireless area network (WAN), a wired connection, or the like. Thus, the primary device may act as an intermediary between the secondary device and the remote system for configuring the secondary device.

Abstract: Techniques for training a machine-learning model are described. In an example, a computer generates a first pseudo-label indicating a first mask associated with a first object detected by a first machine-learning model in a first training image. A transformed image of the first training image can be generated using a transformation. Based on the transformation, a second pseudo-label indicating a second mask detected in the transformed image and corresponding to the first mask can be determined. A second machine-learning model can be trained using the second pseudo-label. The trained, second machine-learning model can detect a third mask associated with a second object based on a second image.

Abstract: Systems and methods for automatically prioritizing computing resource configurations for remediation include receiving information describing configuration issues that may result in impaired system performance or unauthorized access, parsing that information and automatically analyzing configuration details of a user's private computing environment to determine that assets provide an environment in which configuration issues may be exploited to produce undesired results. Such systems and methods can generate assessments indicating the likelihood an issue can be exploited and potential impacts of the issue being exploited. Such systems and methods can use these assessments to generate a report prioritizing remediation of specific configuration issues for specific vulnerable assets based on the actual configuration of the user's computing resources and the data managed using those resources.

Abstract: When a first search query including an image of an item is received to search for items associated with similar images, a second search query that includes text based on the image is generated. The text may be based on previous queries associated with the depicted item, visual features of the image, or text that is present in the image. The results from the first search query are scored based on their correspondence with the image of the item. Results having a score greater than a threshold are presented first in the output, followed by a selected number of results from the second search query. Results from the first search query that are associated with a score less than the threshold may be presented after the results from the second search query. This presentation increases the likelihood that items presented earlier in the output are relevant to the initial query.

Abstract: Techniques for reducing the latency of content retrieval from a content delivery network include receiving a request from a client device for media content, parsing the request for attributes associated with the request and the client device, and providing the attributes to a machine learning model to perform server-side prediction of an estimated retrieval time of the media content. A quality level for the media content is determined based on the estimated retrieval time, and the requested media content is provided to the client device at the determined quality level.

Abstract: Systems and methods are provided to eliminate multiplication operations with zero padding data for convolution computations. A multiplication matrix is generated from an input feature map matrix with padding by adjusting coordinates and dimensions of the input feature map matrix to exclude padding data. The multiplication matrix is used to perform matrix multiplications with respective weight values which results in fewer computations as compared to matrix multiplications which include the zero padding data.

Abstract: To assist a user in the correct performance of an activity, video data is acquired. A pose of the user is determined from the video data and an avatar is generated representing the user in the pose. The pose of the user is compared to one or more other poses representing correct performance of the activity to determine one or more differences that may represent errors by the user. Depending on the activity that is being performed, some errors may be presented to the user during performance of the activity, while other errors may be presented after performance of the activity has ceased. To present an indication of an error, a specific body part or other portion of the avatar that corresponds to a difference between the user's pose and a correct pose may be presented along with an instruction regarding correct performance of the activity.

Abstract: An autonomous mobile device (AMD) moves around a physical space while performing tasks. The AMD may have sensors with fields of view (FOVs) that are forward-facing. As the AMD moves forward, a safe region is determined based on data from those forward-facing sensors. The safe region describes a geographical area clear of obstacles during recent travel. Before moving outside of the current FOV, the AMD determines whether a move outside of the current FOV keeps the AMD within the safe region. For example, if a path that is outside the current FOV would result in the AMD moving outside the safe region, the AMD modifies the path until poses associated with the path result in the AMD staying within the safe region. The resulting safe path may then be used by the AMD to safely move outside the current FOV.

Abstract: A system and method for providing quantum entanglement using a hybrid space-fiber quantum network are described. The hybrid space-fiber quantum network includes a communications hub located proximate to an optical ground station and also includes an aerial entangled particle source, such as an entangled photon source attached to a satellite, drone, aircraft, etc. An atmospheric or free-space channel is used to distribute quantum entanglement between optical ground stations that are separated by geographic distances, via the aerial entangled particle source. Also, fiber optic links are connected to the communications hub located proximate to the optical ground station. The communications hub includes optical switches that enable any of the fiber optic links connected to the communications hub to receive or send distributed quantum entanglement to a remotely located recipient endpoint via the atmospheric or free-space channel.

Abstract: Systems, devices, and methods are provided for processing images using machine learning. Features may be obtained from an image using a residual network, such as ResNet-101. Features may be analyzed using a classification model such as K-nearest neighbors (K-NN). Features and metadata extracted from images may be used to generate other images. Templates may be used to generate various types of images. For example, assets from two images may be combined to create a third image.

Abstract: Server-specified subscription filters for long-lived client requests to fetch data in response to events. In one aspect, the techniques encompass a method performed by a set of one or more computing devices. The method includes the step of receiving a long-lived request to fetch data in response to events sent by a client computing device. The method further includes receiving a server-specified subscription filter for the long-lived request and executing the long-lived request. Executing the long-lived request includes creating a persistent function that uses the server-specified subscription filter to map a source event stream to a response event stream. The response event stream is provided to the client computing device. The server-specified subscription filter facilitates filtering of events fetched for the long-lived request in a way that may not be possible or impractical if the subscription client were required to specify the filter in the long-lived request.

Abstract: Implementations detailed herein include description of a computer-implemented method.

Abstract: Devices, systems, and methods are provided for enhanced geographical caching of estimated arrival times. A method may include receiving respective user inputs indicative of respective users being in transit to a destination location from within a geographic region; determining, for the first user and the second user, a first estimated time of arrival from a first geographical area to the destination location, the first geographical area including the first location and the second location; identifying a third location of the first device at a third time, wherein the third location is within the first geographical area; determining that a time-to-live (TTL) of the first estimated time of arrival has not expired at the third time; and refraining from recalculating the first estimated time of arrival.

Abstract: User identities can managed at an organization level, instead of across multiple individual resource accounts. In a resource provider environment, access to various resources and services may require users to have identities with specific resource accounts. Users can instead be associated with organization accounts, or virtual accounts that are not associated with specific resources or services. The organization accounts are attached at the appropriate location(s) in an organizational hierarchy. A user having an organization account can project the identity in any sub-account in the organization hierarchy. This can include any lower-level resource account, or can child accounts under a relevant branch of the hierarchy. A user can validate against the organization account, and receive access to the relevant service or resources using the identity projected in the corresponding resource account.

Abstract: Systems and methods to measure and affect focus, engagement, and presence of users may include measuring a variety of aspects of users engaged in particular activities. Individual user characteristics or preferences and attributes of activities may be taken into account to determine levels of focus for particular users and activities. A variety of sensors may detect aspects of users engaged in activities to measure levels of focus. In addition, a variety of output devices may initiate actions to affect levels of focus of users engaged in activities. Further, a variety of processing algorithms, including machine learning models, may be trained to identify desired levels of focus, to calculate current levels of focus, and to select actions to change or boost levels of focus. In this manner, activities undertaken by users, as well as interactions between multiple users, may be made more engaging, efficient, and productive.

Abstract: Video output is synchronized to the actions of a user by determining positions of the user's body based on acquired video of the user. The positions of the user's body are compared to the positions of a body shown in the video output to determine corresponding positions in the video output. The video output may then be synchronized so that the subsequent output that is shown corresponds to the subsequent position attempted by the user. The rate of movement of the user may be used to determine output characteristics for the video to cause the body shown in the video output to appear to move at a similar rate to that of the user. If the user moves at a rate less than a threshold or performs an activity erroneously, the video output may be slowed or portions of the video output may be repeated.

Abstract: The following description is directed to a logic repository service. In one example, a method of a logic repository service can include receiving a first request to generate configuration data for configurable hardware using a specification for application logic of the configurable hardware. The method can include generating the configuration data for the configurable hardware. The configuration data can include data for implementing the application logic. The method can include encrypting the configuration data to generate encrypted configuration data. The method can include signing the encrypted configuration data using a private key. The method can include transmitting the signed encrypted configuration data in response to the request.

Abstract: Techniques and systems can process data of a dataset to determine when a portion of data is comprised in the data of the dataset. An output generated from processing the data of the dataset can be evaluated, where the output can signify that processing the data of the dataset was unable to locate the portion of data in the data of the dataset. Based on evaluating the output, the data of the dataset can be automatically reprocessed to determine the portion of data is in the data of the dataset. A result can then be generated from the portion of data determined to be in the data of the dataset.

Abstract: A speech-processing system may provide access to one or more virtual assistants via a voice-controlled device. A user may leverage a first virtual assistant to translate a natural language command from a first language into a second language, which the device can forward to a second virtual assistant for processing. The device may receive a command from a user and send input data representing the command to a first speech-processing system representing the first virtual assistant. The device may receive a response in the form of a first natural language output from the first speech-processing system along with an indication that the first natural language output should be directed to a second speech-processing system representing the second virtual assistant. For example, the command may be in the first language, and the first natural language output may be in the second language, which is understandable by the second speech-processing system.

Abstract: Techniques for determining whether audio is machine-outputted or non-machine-outputted are described. A device may receive audio, may process the audio to determine audio data including audio features corresponding to the audio, and may process the audio data to determine audio embedding data. The device may process the audio embedding data to determine whether the audio is machine-outputted or non-machine-outputted. In response to determining that the audio is machine-outputted, then the audio may be discarded or not processed further. Alternatively, in response to determining that the audio is non-machine-outputted (e.g., live speech from a user), then the audio may be processed further (e.g., using ASR processing).

Abstract: This disclosure describes a distributed automated mobile vehicle (“automated mobile vehicle”) system for autonomously delivering orders of items to various delivery locations and/or autonomously returning items to a return location. In some implementations, each user may own or be assigned their own automated mobile vehicle that is associated with the user and an automated mobile vehicle control system maintained by the user. When the user orders an item, the user owned or controlled automated mobile vehicle navigates to a materials handling facility, retrieves the ordered item and delivers it to the user.

Abstract: In one example, a neural network accelerator can execute a set of instructions to: load a first weight data element from a memory into a systolic array, the first weight data element having first coordinates; extract, from the instructions, information indicating a first subset of input data elements to be obtained from the memory, the first subset being based on a stride of a transposed convolution operation and second coordinates of first weight data element in a rotated array of weight data elements; based on the information, obtain the first subset of input data elements from the memory; load the first subset of input data elements into the systolic array; and control the systolic array to perform first computations based on the first weight data element and the first subset of input data elements to generate output data elements of an array of output data elements.

Abstract: An electric pallet jack can be configured to include logic controllers that are connected to a drive system and a steering system of the electric pallet jack. The logic controllers can be in communication with one or more sensors that enable determinations of pallet jack velocity, pallet jack acceleration, and a rate of turning for the electric pallet jack. The logic controllers can be configured to provide maximum velocity, maximum acceleration, maximum deceleration, and maximum rate of turning limitations to maintain control over an object transported by the electric pallet jack. The logic controllers can determine whether the maximum thresholds of the electric pallet jack are exceeded by an operating variable and can modulate the amount of power provided by the drive system to reduce the operating variable below the associated threshold.

Abstract: An update service of a provider network transmits an update to an edge device by opportunistically selecting one communication channel (or transmission bandwidth) over another (e.g., based on analysis of performance metrics associated with the channel) to transmit different portions of the update to the edge device. For example, the update service may choose the channel with highest available bandwidth or the channel with the lowest failure rates. The update service may receive indications from the edge device that transmission of different update portions was successful. In some cases, the edge device itself may instead perform the selection of one communication channel over another (e.g., based on analysis of channel metrics) to receive different portions of the update at the edge device. The edge device may transmit indications that the edge device successfully received different portions of the update.

Abstract: Systems and methods authenticate storage devices. In one implementation, a computer-implemented method is provided for authenticating a storage device. According to the method, a manifest that identifies a destination is receive. A transfer station reads a digital signature from the storage device. The digital signature is validated and, based on the validation of the digital signature, a transfer of one or more files from the storage device via the transfer station is authorized to the destination identified in the manifest.

Abstract: A system comprising one or more computers implements a synthetic sensor service configured to deploy synthetic sensors to an in-vehicle computing device implementing a synthetic sensor orchestration environment for a vehicle. The synthetic sensor orchestration environment determines a placement decision for a new synthetic sensor to be added to the vehicle based on one or more annotations included in a synthetic sensor package for the new synthetic sensor. The synthetic sensor service and respective synthetic sensor orchestration environments implemented in various types of vehicles provide a consistent way to remotely add additional synthetic sensors and/or other functionality to different types of vehicles after the vehicles have already been put in use by respective owners or operators of the vehicles.

Abstract: Systems and methods are described herein for detecting the inadvertent modification to or deletion of data in a data store and taking automated action to prevent the deletion of data from becoming permanent. The described techniques may also be utilized to detect anomalous changes to a policy or affecting storage of data and taking automated action to mitigate the effects of those changes. In one example, events generated as a result of requests to perform operations on data objects in a data storage service may be obtained, where at least some of the events indicate a failure to fulfill respective requests. Data from the events may be input into a model to detect an anomaly indicative of inadvertent modification of data. As a result of detection of the anomaly, a set of operations may be initiated or performed to prevent the inadvertent modification of data from becoming permanent.

Abstract: To accelerate the data processing of a processor, a coprocessor subsystem can be used to offload data processing operations from the processor. The coprocessor subsystem can include a coprocessor and an accelerator. The accelerator can offload operations such as data formatting operations from the coprocessor to improve the performance of the coprocessor. The coprocessor subsystem can be used to accelerate database operations.

Abstract: Systems and methods are disclosed for automated lateral transfer and elevation of sortation shuttles. An example system may include a track having a first portion arranged in a first direction, a shuttle configured to move along the track, and a shuttle carriage system configured to move in a second direction transverse to the first direction, where the shuttle is configured to move from the track to the shuttle carriage system. The shuttle carriage system may include a first frame configured to support the shuttle, a first electromagnet configured to propel the first frame, and a second electromagnet coupled to the first frame, the second electromagnet configured to propel the shuttle off the first frame.

Abstract: Working set ratio estimations of data items in a sliding time window are determined to dynamically allocate storage for the data items. A working set ratio may be determined by accessing a fixed-size array that stores respective timestamps of last accesses of data items to determine which data items are useful to determine an estimate of a working set for the application within a range of time. The working set ratio is then determined from an estimated working set and an amount of computing resources allocated to the application by the estimated working set. The amount of the computing resources allocated to the application may then be automatically scaled according to the determine working set ratio.

Abstract: Techniques and systems can receive a query identifying a name linked to performance data of a computer system and a location of the performance data. The name linked to the performance data of the computer system and the location of the performance data can be communicated to a first computer-implemented system. The first computer-implemented system can include identifying data derived from the name and the location of the performance data. Identifying data derived from the name and the location of the performance data can be received from the first computer-implemented system. The identifying data derived from the name and the location of the performance data can be used to retrieve the performance data. The performance data can be hosted by a second computer-implemented system that is different than the first computer-implemented system.

Abstract: A system configured to improve sound source localization (SSL) processing by reducing a number of direction vectors and grouping the direction vectors into direction cells is provided. The system performs clustering to generate a smaller set of direction vectors included in a delay-direction codebook, reducing a size of the codebook to the number of unique delay vectors. In addition, the system groups the direction vectors into direction cells having a regular structure (e.g., predetermined uniformity and/or symmetry), which simplifies SSL processing and results in a substantial reduction in computational cost. The system may also select between multiple codebooks and/or dynamically adjust the codebook to compensate for changes to the microphone array. For example, a device with a microphone array fixed to a display that can tilt may adjust the codebook based on a tilt angle of the display to improve accuracy.

Abstract: A distributed storage system may store data object instances in persistent storage and may store keymap information for those data object instances in a distributed hash table on multiple computing nodes. Each data object instance may include a composite key containing a user key. The keymap information for each data object instance may map the user key to a locator and the locator to the data object instance. A request to store or retrieve keymap information for a data object instance may be routed to a particular computing node based on a consistent hashing scheme in which a hash function is applied to a portion of the composite key of the data object instance. Thus, related entries may be clustered on the same computing nodes. The portion of the key to which the hash function is applied may include a pre-determined number of bits or be identified using a delimiter.

Abstract: The updating of a definition layer or schema for a large distributed database can be accomplished using a plurality of data store tiers. A distributed database can be made up of many individual data stores, and these data stores can be allocated across a set of tiers based on business logic or other allocation criteria. The update can be applied sequentially to the individual tiers, such that only data stores for a single tier are being updated at any given time. This can help to minimize downtime for the database as a whole, and can help to minimize problems that may result from an unsuccessful update. Such an approach can also allow for simplified error detection and rollback, as well as providing control over a rate at which the update is applied to the various data stores of the distributed database.

Abstract: Systems and methods for durable storage of storage volume “snapshots” are provided. Snapshots are stored as collections of snapshot data objects. To improve the durability of snapshot storage, physical deletion of snapshot data objects may be delayed for a period of time after the snapshot data objects are marked for deletion. Lists of the stored snapshot data objects and the snapshot data objects that make up active snapshots may be periodically analyzed. If there are any snapshot data objects that are part of active snapshots and are not present in the list of stored snapshot data objects, the snapshot data objects may be recovered before they are physically deleted.

Abstract: Intelligent query routing may be performed across shards of a scalable database table. A router of a database system may receive an access request directed to one or more database tables. The router may evaluate the access request with respect to metadata obtained for the database tables to determine an assignment distribution of computing resources of the database system to data that can satisfy the access request. The router can select planning locations to perform the access request based on the assignment distribution of the computing resources. The router can cause the access request to be performed according to planning at the selected planning locations.

Abstract: At a managed control plane service, constituent services and operational requirements of an application are identified. In response to an end-user request directed to the application, contents of an inter-service request are generated at a resource selected by the managed control plane service for a first constituent service, and a response to the message is generated at another resource selected for a second constituent service. Tasks to be performed for the operational requirements are initiated by the managed control plane service.

Abstract: Index management for non-relational database systems may be automatically performed. Performance of queries to a non-relational database may be evaluated to determine whether to create or remove an additional index. An additional index may be automatically created to store a subset of data projected from the non-relational database to utilize when performing a query to the non-relational database instead of accessing data in the non-relational database.

Abstract: Described herein is a system for predictive feature analysis to precompute and store data required to respond to a user input in advance of receiving the user input. To determine when to precompute the data, the system uses a prediction model to predict user interactions and when to expect the user input. The system predicts that a user input is about to be received, and starts to process certain data to determine feature data and stores the data in a cache. When the user input is received, the system retrieves the data from the cache for further processing to respond to the user input.

Abstract: Devices and techniques are generally described for determining named entity recognition tags. In various examples, first input data representing a natural language input may be determined. In some examples, a first machine learned model may determine first data comprising a first encoded representation of the first input data. In various examples, second data representing a grouping of text of the first input data may be determined based at least in part on the first data. In some examples, first entity data may be determined by searching a memory layer using the second data. In at least some examples, the first entity data and the first data may be combined to generate third data. In various examples, output data comprising a predicted named entity recognition tag may be generated for the grouping of text based at least in part on the third data.

Abstract: An interruption-handling setting for a category of interactions of an application is determined via a programmatic interface. A set of user-generated input is obtained while presentation to a user of a set of output of the category is in progress. A response to the set of user-generated input is prepared based at least in part on the interruption-handling setting.

Abstract: Embodiments of a contextualized visual search (CVS) system are disclosed capable of isolating target images of items that contain instances of a previously-unseen query image from a large database of target images. In embodiments, the system is used to implement an interactive query interface of an e-commerce portal, which allows the user to specify the query image (e.g. a logo) to be searched. The system converts the query image into a feature vector using a first machine learning model, and compares the feature vector to feature vectors of target images using a second machine learning model to find matching target images that contain an instance of the query image. The system then returns a query result indicating a list of items associated with matched target images. In embodiments, the query results may be ranked based on a set of personalized factors associated with the user.

Abstract: Methods, apparatuses, and systems for a web services provider to interact with a client on remote job execution. For example, a web services provider may receive a job command, from an interactive programming environment of a client, applicable to job for a machine learning algorithm on a web services provider system, process the job command using at least one of a training instance and an inference instance, and provide metrics and log data during the processing of the job to the interactive programming environment.

Abstract: An Identity and Access Management Service implements persistent source values PSVs) for assumed identities. A source value (e.g., an original identifier of an entity) is persisted across assumed identities, facilitating identification of entities (users or applications) responsible for actions taken by the assumed (e.g., alternative) identities. The Manager receives a request to assume an identity. The request includes the entities current credentials and a PSV. The current credentials are authenticated and a persistent source value policy may be relied on to determine whether and/or how to grant the assumed identity. The PSV may be copied from credentials in the request in order to be included in the credentials for the requested identity that the Manager provides in response to the request. Use of the requested credentials, including the PSV, to access services or resources may be logged, the logs including the PSV from the request to assume the identity.

Abstract: Techniques are provided herein for selecting and transmitting snippets from a messaging application. A “snippet” refers to an audio segment of a song that is less than the whole of the song. A user may request to view various audio segments (e.g., by category, by search, etc.) corresponding to portions of respective songs via a user interface of the messaging application. In some embodiments, an audio segment can be selected and metadata associated with that particular audio segment may be transmitted to another computing device where the audio segment can be played (e.g., streamed). In this manner, these snippets can be employed by the user to enhance their chat or texting conversation.

Abstract: Disclosed are various embodiments for discovering availability of digital media titles from multiple digital media service providers. A control is presented to establish a relationship between a user account and a first digital media service provider. A first availability for access by the user account of a digital media title is received from the first digital media service provider. A second availability for access by the user account of the digital media title is received from a second digital media service provider. An indication of availability for access of the digital media title by the user account from the first digital media service provider and the second digital media service provider is presented based at least in part on the first availability and the second availability.