Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing critical section subgraphs in a computational graph system. One of the methods includes executing a lock operation including providing, by a task server, a request to a value server to create a shared critical section object. If the task server determines that the shared critical section object was created by the value server, the task server executes one or more other operations of the critical section subgraph in serial. The task server executes an unlock operation including providing, by the task server, a request to the value server to delete the shared critical section object.

Abstract: Methods, systems, and apparatus, for automatically changing a network system. A method includes receiving a set of first intents that describe a state of a first switch fabric; receiving a set of second intents that describe a state of a second switch fabric; computing a set of network operations to perform on the first switch fabric to achieve the second switch fabric, the set of operations also defining an order in which the operations are to be executed, and the set of operations determined based on the set of first intents, the set of second intents, and migration logic that defines a ruleset for selecting the operations based on the set of first intents and the second intents; and executing the set of network operations according to the order, to apply changes to elements within the first switch fabric to achieve the state of the second switch fabric.

Abstract: A method at an electronic device with one or more microphones and a speaker, the electronic device configured to be responsive to any of a plurality of affordances including a voice-based affordance, includes determining background noise of an environment associated with the electronic device, and before detecting the voice-based affordance: determining whether the background noise would interfere with recognition of the hotword in voice inputs detected by the electronic device, and if so, indicating to a user to use an affordance other than the voice-based affordance.

Abstract: A method for minimizing scan disruptions includes receiving a scan request requesting to scan a set of network-connected assets. Each network-connected asset is associated with corresponding network characteristics. The method includes partitioning the set of network-connected assets into a plurality of groups based on the corresponding network characteristics. For each respective group, simultaneously, the method includes determining an ordered list for scanning each network-connected asset in the respective group, scanning a first network-connected asset of the respective group based on the ordered list, and, after scanning the first network-connected asset, determining a post-scan health status of the first network-connected asset. The method includes determining, using the post-scan health status, that a health of the first network-connected asset is degraded.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes receiving a training image and a ground truth super-resolution image; processing a first training network input comprising the training image using the neural network to generate a first training super-resolution image; processing a first critic input generated from (i) the training image and (ii) the ground truth super-resolution image using a critic neural network to map the first critic input to a latent representation; processing a second critic input generated from (i) the training image and (ii) the first training super-resolution image using the critic neural network to map the second critic input to a latent representation; determining a gradient of a generator loss function that measures a distance between the latent representations of the critic inputs; and determining an update to the parameters.

Abstract: In a general aspect, a system for media playback can include a first media playback device configured to receive a media stream from a media casting device over a data network, the first media playback device being a member of the media playback group and a second media playback device configured to receive the media stream, the second media playback device being a member of the media playback group. The first media playback device and the second media playback device can be collectively configured to designate one of the first media playback device and the second media playback device as a leader playback device of the media playback group. The playback device not designated as the leader playback device can be designated as a follower playback device of the media playback group. The first media playback device and the second media playback device can be further collectively configured to determine a clock offset between the leader playback device and the follower playback device.

Abstract: Systems and methods are provided in which physical objects in the ambient environment can function as user interface implements in an augmented reality environment. A physical object detected within a field of view of a camera of a computing device may be designated as a user interface implement in response to a user command. User interfaces may be attached to the designated physical object, to provide a tangible user interface implement for user interaction with the augmented reality environment.

Abstract: A method for using a user-fillable form in a host container includes receiving, at a host container, a user-fillable form bound to dynamic data from an underlying data source where the user-fillable form has a data structure generated by prepopulated coding. The method further includes translating the user-fillable form into a hostable format for the host container. The method also includes rendering, using the hostable format for the host container, the user-fillable form in a user interface. The method further includes receiving, at the user interface of the host container, from a user of the host container, a data entry for input to the user-fillable form and updating, by the host container, the dynamic data from the underlying data source by persisting data from the data entry in a data store associated with the underlying data source.

Abstract: This document describes techniques directed to active thermal-control of a floodlight and associated floodlights. As described, an example floodlight includes a first heat-transfer subsystem that uses a fully enclosed heat sink to transfer heat from an array of LEDs to a first housing component of the floodlight. The floodlight further includes a second heat-transfer subsystem to transfer heat from one or more PSUs to a second housing component of the floodlight. Described techniques include using thermistors located throughout the floodlight to actively monitor a temperature profile within the floodlight and, if one or more operating-temperature thresholds are violated, reducing power consumption within the floodlight.

Abstract: On-demand application permissions is described, including obtaining one or more consents associated with one or more functions of an application, where the application does not allow using the functions without associated consents; receiving, from a user, a consent associated with a function; activating to allow that function to be executed; when a request from the user to use another function is received, determining that the another function requires an associated consent to activate; determining that there is no consent from the user associated with the another function; prompting for a consent associated with the another function; receiving the consent associated with another function; and activating to allow the another function to be executed.

Abstract: A method for a proxyless protocol includes intercepting, from a client, a first Transmission Control Protocol (TCP) connection request requesting to establish a TCP connection between the client and a proxy for routing data to a destination server. The request includes client information and a first sequence number. The method also includes transmitting, to the destination server, a second TCP connection request to establish a TCP connection between the client and the destination server. The second request includes a second sequence number less than the first sequence number. The method also includes intercepting, from the destination server, an acknowledgment message indicating acknowledgment of the second TCP connection request. The method also includes transmitting, to the destination server, a proxy protocol header message with the client information.

Abstract: Methods, systems, and computer storage media for implementing neural networks in fixed point arithmetic computing systems. In one aspect, a method includes the actions of receiving a request to process a neural network using a processing system that performs neural network computations using fixed point arithmetic; for each node of each layer of the neural network, determining a respective scaling value for the node from the respective set of floating point weight values for the node; and converting each floating point weight value of the node into a corresponding fixed point weight value using the respective scaling value for the node to generate a set of fixed point weight values for the node; and providing the sets of fixed point floating point weight values for the nodes to the processing system for use in processing inputs using the neural network.

Abstract: The present disclosure describes apparatuses and techniques of adaptive PLMN management for varying network conditions. In some aspects, a PLMN manager of a user equipment (UE) searches, as part of a registration procedure, a data repository of PLMN information that includes a PLMN blocked from registration for a duration of time and determines that the PLMN is blocked due to a signal-related condition with a cell of the PLMN (e.g., weak signal). The PLMN manager then determines, during the duration of time, that the signal-related condition between the UE and the cell has improved. In response to the improvement, the PLMN manager unblocks the PLMN before expiration of the duration of time. By so doing, the UE may reattempt registration with the unblocked PLMN at least once before the duration of time expires, which may allow the UE to register more quickly and reestablish network services.

Abstract: A method includes receiving, during playback of a content item in a content player of a first mobile application presented on a client device of a first user, an indication of a user request pertaining to a second mobile application, the user request corresponding to a first point in the content item played in the content player of the first mobile application. The method additionally includes causing the playback of the content item to continue in the content player presented on a client device while a user interface of the second mobile application is displayed on the client device, wherein the content player persists on top of the user interface of the second mobile application to provide the playback of the content item in a continuous manner from the first point in the content item.

Abstract: Systems and methods for pre-training and fine-tuning of neural-network-based language models to reason directly over tables without generating logical forms. In some examples, a language model can be pre-trained using masked-language modeling tasks synthetically generated from tables pulled from a knowledge corpus. In some examples, the language model may be further pre-trained using pairs of counterfactual statements generated from those tables, and/or one or more statements that compare selected data from those tables. The language model may then be fine-tuned using examples that include only a question, an answer, and a table, allowing fine-tuning examples to be harvested directly from existing benchmark datasets or synthetically generated.

Abstract: Guiding purchasing via smartphone by, determining, via smartphone input of a user, the smartphone user's intent to purchase a given product. At least one sequence of tasks to purchase each of a plurality of products is determined. The determined intent to purchase the given product is associated with a determined sequence of tasks to purchase one of the products in the plurality of products. The smartphone user's current state in the associated sequence of tasks is determined. The smartphone user is notified, via the smartphone, of the next uncompleted task from the associated sequence of tasks based on the smartphone user's current state in the associated sequence of tasks.

Abstract: A method includes receiving a set of video frames that correspond to a video, including a first video frame and a second video frame that each include a face, wherein the second video frame is subsequent to the first video frame. The method further includes performing face tracking on the first video frame to identify a first face resampling keyframe and performing face tracking on the second video frame to identify a second face resampling keyframe. The method further includes deriving an interpolation amount. The method further includes determining a first interpolated face frame based on the first face resampling keyframe and the interpolation amount. The method further includes determining a second interpolated face frame based on the second face resampling keyframe and the interpolation amount. The method further includes rendering an interpolated first face and an interpolated second face. The method further includes displaying a final frame.

Abstract: Methods and systems for encoder parameter setting optimization. A media item to be provided to one or more users of a platform is identified. The media item is associated with a media class. An indication of the identified media item is provided as input to a first machine learning model. The first machine learning model is trained to predict, for a given media item, a set of encoder parameter settings that satisfy a performance criterion in view of a respective media class associated with the given media item. One or more outputs of the first machine learning model are obtained. The one or more obtained outputs include encoder data identifying one or more sets of encoder parameter settings and, for each of the sets of encoder parameter settings, an indication of a level of confidence that a respective set of encoder parameter settings satisfies the performance criterion in view of the media class associated with the identified media item.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reliably performing data compression and data decompression across a wide variety of hardware and software platforms by using integer neural networks. In one aspect, there is provided a method for entropy encoding data which defines a sequence comprising a plurality of components, the method comprising: for each component of the plurality of components: processing an input comprising: (i) a respective integer representation of each of one or more components of the data which precede the component in the sequence, (ii) an integer representation of one or more respective latent variables characterizing the data, or (iii) both, using an integer neural network to generate data defining a probability distribution over the predetermined set of possible code symbols for the component of the data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing topological scheduling on a machine-learning accelerator having an array of tiles. One of the methods includes performing, at each time step of a plurality of time steps corresponding respectively to columns within each of a plurality of wide columns of the tile array, operations comprising: performing respective multiplications using tiles in a respective tile column for the time step, computing a respective output result for each respective tile column for the time step including computing a sum of results of the multiplications for the tile column, and storing the respective output result for the tile column in a particular output RAM having a location within the same tile column and on a row from which the output result will be read by a subsequent layer of the model.