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: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for allocating computing resources. In one aspect, a method includes receiving intent data specifying one or more computing services to be hosted by a computing network, requested characteristics of computing resources for use in hosting the computing service, and a priority value for each requested characteristic. A budget constraint is identified for each computing service. Available resources data is identified that specifies a set of available computing resources. A resource allocation problem for allocating computing resources for the one or more computing resources is generated based on the intent data, each budget constraint, and the available resources data. At least a portion of the set of computing resources is allocated for the one or more computing services based on results of evaluating the resource allocation problem to meet a particular resource allocation objective.

Abstract: The present disclosure relates to generating and adjusting translated audio from a video-based source. The method includes receiving video data and corresponding audio data in a first language; generating a translated preliminary transcript in a second language; aligning timing windows of portions of the translated preliminary transcript with corresponding segments of the audio data; determining portions of the translated aligned transcript in the second language that exceed a timing window range of the corresponding segments of the audio data in the first language to generate flagged transcript portions; transmitting the original transcript, the translated aligned transcript, and the first speech dub to a first device, the generated flagged transcript portions included in the original transcript and the translated aligned transcript; receiving, from the first device, a modified original transcript; and generating, based on the modified original transcript, a second speech dub in the second language.

Abstract: Operations of a method include receiving a configuration request requesting configuration management of a base configuration package that describes infrastructure of an application. The operations include determining, for the base configuration package, a plurality of package functions. Each package function of the plurality of package functions extends functionality of the base configuration package. The operations include determining, for the base configuration package and the plurality of package functions, a change-proposal function. The change-proposal function proposes one or more of the plurality of package functions to extend the functionality of the base configuration package. The operations include transmitting, to a user device, the change-proposal function and receiving, from the user device, approval of the change-proposal function.

Abstract: Hardware transactions or other techniques, such as custom PCIe handling devices, are used to atomically move pages from one host's memory to another host's memory. The hosts are connected by one or two non-transparent bridges (NTBs), which make each host's memory and devices available to the other, while allowing each host to reboot independently.

Abstract: A method includes receiving a point data anomaly detection query from a user. The query requests the data processing hardware to determine a quantity of anomalous point data values in a set of point data values. The method includes training a model using the set of point data values. For at least one respective point data value in the set of point data values, the method includes determining, using the trained model, a variance value for the respective point data value and determining that the variance value satisfies a threshold value. Based on the variance value satisfying the threshold value, the method includes determining that the respective point data value is an anomalous point data value. The method includes reporting the determined anomalous point data value to the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection. In one aspect, a method comprises: obtaining: (i) an image, and (ii) a set of one or more query embeddings, wherein each query embedding represents a respective category of object; processing the image and the set of query embeddings using an object detection neural network to generate object detection data for the image, comprising: processing the image using an image encoding subnetwork of the object detection neural network to generate a set of object embeddings; processing each object embedding using a localization subnetwork to generate localization data defining a corresponding region of the image; and processing: (i) the set of object embeddings, and (ii) the set of query embeddings, using a classification subnetwork to generate, for each object embedding, a respective classification score distribution over the set of query embeddings.

Abstract: Example techniques are provided for the task of differentially private clustering. For several basic clustering problems, including Euclidean DensestBall, 1-Cluster, k-means, and k-median, the present disclosure provides efficient differentially private algorithms that achieve essentially the same approximation ratios as those that can be obtained by any non-private algorithm, while incurring only small additive errors. This improves upon existing efficient algorithms that only achieve some large constant approximation factors.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neural network compression. In one aspect, a method comprises receiving a neural network and identifying a particular set of multiple weights of the neural network. Multiple anchor points are determined based on current values of the particular set of weights of the neural network. The neural network is trained by, at each of multiple training iterations, performing operations comprising adjusting the values of the particular set of weights by backpropagating gradients of a loss function. The loss function comprises a first loss function term based on a prediction accuracy of the neural network and a second loss function term based on a similarity of the current values of the particular set of weights to the anchor points. After training, the values of the particular set of weights are quantized based on the anchor points.

Abstract: To reduce the effects of traffic jams, a traffic reduction system identifies road segments having more a threshold amount of traffic. The traffic reduction system also receives an indication of a current location of a client device operating in a vehicle and compares the current location to the locations of the identified road segments to determine whether the vehicle is on or approaching the road segment. If the vehicle is on or approaching the road segment, the traffic reduction system determines a target speed for the vehicle to maintain an equal distance between the vehicle and the vehicle in front of the vehicle and the vehicle and the vehicle behind the vehicle. The traffic reduction system then provides the target speed to the client device for display on a user interface. By maintaining equal distances between vehicles in front of and behind each other, the amount of traffic dissipates.

Abstract: Methods, systems, and apparatus for receiving, by a voice action system, data specifying trigger terms that trigger an application to perform a voice action and a context that specifies a status of the application when the voice action can be triggered. The voice action system receives data defining a discoverability example for the voice action that comprises one or more of the trigger terms that trigger the application to perform the voice action when a status of the application satisfies the specified context. The voice action system receives a request for discoverability examples for the application from a user device having the application installed, and provides the data defining the discoverability examples to the user device in response to the request. The user device is configured to provide a notification of the one or more of the trigger terms when a status of the application satisfies the specified context.

Abstract: A method for training a speech recognition model includes receiving a set of training utterance pairs each including a non-synthetic speech representation and a synthetic speech representation of a same corresponding utterance. At each of a plurality of output steps for each training utterance pair in the set of training utterance pairs, the method also includes determining a consistent loss term for the corresponding training utterance pair based on a first probability distribution over possible non-synthetic speech recognition hypotheses generated for the corresponding non-synthetic speech representation and a second probability distribution over possible synthetic speech recognition hypotheses generated for the corresponding synthetic speech representation. The first and second probability distributions are generated for output by the speech recognition model.

Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.

Abstract: Methods, systems, and computer-readable media are provided for collective reconciliation. In some implementations, a query is received, wherein the query is associated at least in part with a type of entity. One or more search results are caused to be generated based at least in part on the query. Previously generated data is retrieved associated with at least one search result of the one or more of search results, the data comprising one or more entity references in the at least one search result corresponding to the type of entity. The one or more entity references are ranked, and an entity result is selected from the one or more entity references based at least in part on the ranking. An answer to the query is provided based at least in part on the entity result.

Abstract: To present augmented reality features without localizing a user, a client device receives a request for presenting augmented reality features in a camera view of a computing device of the user. Prior to localizing the user, the client device obtains sensor data indicative of a pose of the user, and determines the pose of the user based on the sensor data with a confidence level that exceeds a confidence threshold which indicates a low accuracy state. Then the client device presents one or more augmented reality features in the camera view in accordance with the determined pose of the user while in the low accuracy state.

Abstract: This disclosure describes methods, apparatuses, and techniques for capturing a fingerprint image using an electronic device with an under-display fingerprint sensor (UDFPS) embedded under a display screen of a display system. The display system utilizes a pulse-width modulation circuit to generate a pulse-width modulated (PWM) signal to control light emitted by the display screen. As the display screen illuminates a user's touch, the UDFPS captures light reflected off the user's touch, therefore, capturing the fingerprint image. The captured fingerprint image, however, includes a PWM noise. The electronic device uses a noise-filtering algorithm to filter out and/or reduce the PWM noise in the captured fingerprint image. In one aspect, the noise-filtering algorithm estimates and/or determines the PWM noise in the captured fingerprint image. The noise-filtering algorithm then reduces, extracts, and/or filters out the PWM noise from the captured fingerprint image.

Abstract: Various arrangements for using captured voice to generate a custom interface controller are presented. A vocal recording from a user may be captured in which a spoken command and multiple smart-home devices are indicated. One or more common functions that map to the multiple smart-home devices may be determined. A custom interface controller may be generated that controls the one or more common functions of each smart-home device of the multiple smart-home devices.

Abstract: A method includes receiving, from a first device, a first request indicating a client characteristic, generating a second request for content that simulates a data request originating at a client device with the client characteristic, identifying data of a response to the generated second request, and providing, to the first device, a report based on the identified data.

Abstract: A cloud network is a complex environment in which hundreds and thousands of users or entities can each host, create, modify, and develop multiple virtual machines. Each virtual machine can have complex behavior unknown to the provider or maintainer of the cloud. Technologies disclosed include methods, systems, and apparatuses to monitor the complex environment to detect network anomalies using machine learning techniques. In addition, techniques to modify and adapt to user feedback are provided allowing the developed models to be tuned for specific use cases, virtual machine types, and users.

Abstract: A device for generating a qubit control signal includes: a first signal envelope generator circuit including a first multiple of signal sources, in which an output of each signal source of the first multiple of signal sources is combined to provide a first cumulative output; and a first mixer circuit coupled to the first signal envelope generator circuit, in which the first cumulative output is coupled to a first input of the first mixer circuit, and an output of the first mixer circuit includes a first qubit control signal.

Abstract: Systems and methods for content storage and retrieval are disclosed herein for accessing portions of a file at a client device. A client device receives a request to access a file at the client device. The file includes file portions that are stored at a web-based storage system in communication with the client device via a network. The client device provides the web-based storage system with access to a metafile stored on the client device. The metafile includes an identifier for each of the file portions for the file and an indication of whether each of the file portions are already stored on the client device. In response to the web-based storage system accessing the metafile stored on the client device to identify a set of file portions that is not stored on the client device, the client device receives the identified set of file portions from the web-based storage system via the network.

Abstract: In one general aspect, a computing device includes a hardware processor, a memory, a first housing portion including a touch screen display, and a second housing portion coupled to the first housing portion by a hinge, where the second housing portion includes a rotatable keyboard.

Abstract: This disclosure describes methods and compositions for protein and peptide sequencing.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for transformation for machine learning pre-processing. In some implementations, an instruction to create a model is obtained. A determination is made whether the instruction specifies a transform. In response to determining that the instruction specifies a transform, a determination is made as to whether the transform requires statistics on the training data. The training data is accessed. In response to determining that the transform requires statistics on the training data, transformed training data is generated from both the training data and the statistics. A model is generated with the transformed training data. A representation of the transform and the statistics is stored as metadata for the model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting errors in a client device and its associated applications while preserving the privacy of the user of the device. Methods can include obtaining and blinding contextual application data for an application on a device. Data regarding the application's digital certificate and device trustworthiness data are obtained and provided to a trust assessment server along with the blinded data. This server can provide indications that the device is trustworthy and the application is authentic, and can digitally sign the blinded data. The digital signature can be validated and the unblinded contextual application data can be obtained. If the unblinded data matches the contextual application data, the application can provide the digital signature, the indications, and the unblinded contextual application data to an error detection server, which in turn can indicate the application does not have errors.

Abstract: A method can include determining that a measured distance, of an object in contact with a touchscreen, from a sensor included in the touchscreen, is less than or equal to a first distance and equal to or greater than a second distance, based on determining that the measured distance of the object from the sensor is less than or equal to the first distance and equal to or greater than the second distance, providing haptic feedback as a function of the measured distance, the haptic feedback being greater for smaller measured distances; determining that the measured distance is less than the second distance; and in response to determining that the measured distance is less than the second distance, decreasing the haptic feedback.

Abstract: A frame generation subsystem renders a sequence of frames and a display control subsystem provides a brightness control signal configured to control a brightness of frames displayed at a display panel via pulse width modulation (PWM) of the brightness control signal and determines a deviation in a duty cycle of a first PWM period of the brightness control signal from a default duty cycle resulting from a delayed rendering of a frame. The display control subsystem adjusts a duty cycle of at least a second PWM period to compensate for the deviation in the duty cycle of the first PWM period. The resulting average duty cycle of the brightness control signal over the two frame periods is approximately equal to a default duty cycle and thereby mitigates viewable flicker resulting from the duty cycle change caused by the delayed rendering.

Abstract: A system of multi-modal transmission of packetized data in a voice activated data packet based computer network environment is provided. A natural language processor component can parse an input audio signal to identify a request and a trigger keyword. Based on the input audio signal, a direct action application programming interface can generate a first action data structure, and a content selector component can select a content item. An interface management component can identify first and second candidate interfaces, and respective resource utilization values. The interface management component can select, based on the resource utilization values, the first candidate interface to present the content item. The interface management component can provide the first action data structure to the client computing device for rendering as audio output, and can transmit the content item converted for a first modality to deliver the content item for rendering from the selected interface.

Abstract: Methods, apparatus, and computer readable media related to receiving textual input of a user during a dialog between the user and an automated assistant (and optionally one or more additional users), and generating responsive reply content based on the textual input and based on user state information. The reply content is provided for inclusion in the dialog. In some implementations, the reply content is provided as a reply, by the automated assistant, to the user's textual input and may optionally be automatically incorporated in the dialog between the user and the automated assistant. In some implementations, the reply content is suggested by the automated assistant for inclusion in the dialog and is only included in the dialog in response to further user interface input.

Abstract: The present disclosure describes various aspects of adaptive current control in switching power regulators for fast transient response. In some aspects, a clock of a switching power regulator is prevented, in response to detecting a transient load, from affecting application of current to an inductor of the regulator. A first switch device applies current to the inductor of the regulator until inductor current reaches a maximum current level. A second switch device then enables the current to flow through the inductor until the inductor current reaches a current control signal based on an output voltage of the switching power regulator. In some aspects, an offset is also applied to the current control signal to further increase average inductor current. These operations may be repeated without interruption from the clock to quickly increase the inductor current, and thus current provided to the regulator output in response to the transient load.

Abstract: This document describes a three-party cryptographic handshake protocol in a wireless network in which a sighter receives, from a beacon, a packet including an exponentiation of a random value and a proxy value and generates an end-to-end encrypted ephemeral identifier (E2EE-EID) from the exponentiation of the random value and the proxy value. The sighter generates a message for an owner, selects a private key, and computes an exchanged key using the private key and the E2EE-EID. The sighter extracts a common symmetric key from the exchanged key, encrypts the message using the common symmetric key, and transmits the encrypted message to the owner.

Abstract: An application on a viewer client device receives a user input to access a live stream, sends a request to access the live stream, presents information allowing a user to indicate a first anchor of a plurality of anchors of the live stream, the first anchor corresponding to a timestamp for starting a portion of the live stream, receives the live stream and data indicating the timestamp corresponding to the first anchor of the live stream, and displays the live stream beginning at the timestamp corresponding to the first anchor of the live stream.

Abstract: Systems and methods for optimizing videos are disclosed. A method of the present disclosure includes analyzing a video using a plurality of rules to determine one or more optimizations for the video, the one or more optimizations reflecting a subset of properties to improve viewership statistics of the video by automatically modifying characteristics of the video based on the subset of properties that is indicative of improved viewership statistics pertaining to a plurality of users of a media hosting service, wherein the characteristics comprise at least one characteristic, which when automatically modified, results in a change to the video that correlates to improved viewership statistics pertaining to the plurality of users. The method further includes causing the characteristics of the video to be modified to implement the one or more optimizations, and causing the video with the modified characteristics to be presented to at least a subset of the plurality of users.

Abstract: A method for detecting a hotword includes receiving a sequence of input frames that characterize streaming audio captured by a user device and generating a probability score indicating a presence of a hotword in the streaming audio using a memorized neural network. The network includes sequentially-stacked single value decomposition filter (SVDF) layers and each SVDF layer includes at least one neuron. Each neuron includes a respective memory component, a first stage configured to perform filtering on audio features of each input frame individually and output to the memory component, and a second stage configured to perform filtering on all the filtered audio features residing in the respective memory component. The method also includes determining whether the probability score satisfies a hotword detection threshold and initiating a wake-up process on the user device for processing additional terms.

Abstract: A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected.

Abstract: Methods, systems, and apparatus, including computer-readable media, are described for interleaving memory requests to accelerate memory accesses at a hardware circuit configured to implement a neural network model. A system generates multiple requests that are processed against a memory of the system. Each request is used to retrieve data from the memory. For each request, the system generates multiple sub-requests based on a respective size of the data to be retrieved using the request. The system generates a sequence of interleaved sub-requests that includes respective sub-requests of a first request interleaved among respective sub-requests of a second request. Based on the sequence of interleaved sub-requests, a module of the system receives respective portions of data accessed from different address locations of the memory. The system processes each of the respective portions of data to generate a neural network inference using the neural network model implemented at the hardware circuit.

Abstract: Methods, systems, and apparatus for designing a quantum control trajectory for implementing a quantum gate using quantum hardware. In one aspect, a method includes the actions of representing the quantum gate as a sequence of control actions and applying a reinforcement learning model to iteratively adjust each control action in the sequence of control actions to determine a quantum control trajectory that implements the quantum gate and reduces leakage, infidelity and total runtime of the quantum gate to improve its robustness of performance against control noise during the iterative adjustments.

Abstract: Techniques and apparatuses are described for enabling base station-user equipment messaging regarding deep neural networks. A network entity (base station 121, core network server 320) determines a neural network formation configuration (architecture and/or parameter configurations 1208) for a deep neural network (deep neural network(s) 604, 608, 612, 616) for processing communications transmitted over the wireless communication system. The network entity (base station 121, core network server 302) communicates the neural network formation configuration to a user equipment (UE 110). The user equipment (UE 110) configures a first neural network (deep neural network(s) 608, 612) based on the neural network formation configuration. In implementations, the user equipment (UE 110) recovers information communicated over the wireless network using the first neural network (deep neural network(s) 608, 612).

Abstract: A method includes, for each of a plurality of web resources, receiving, at a communications server, data indicating characteristics of a respective web resource, detecting, based on the received data, that the respective web resource provides functionality for live assistance by a third party content provider through a chat user interface on the respective web resource, and storing, in a database, an entry that indicates that the respective web resource has the functionality. The method includes receiving, from a user, a request to access a particular web resource hosted by a particular third party content provider, determining, based on a stored entry in the database representing the particular web resource, that the web resource provides functionality for live assistance by the particular third party content provider through a particular chat user interface on the web resource, and initiating a chat session between the user and the third party content provider.

Abstract: The present disclosure is directed to an automated neural architecture search approach for designing new neural network architectures such as, for example, resource-constrained mobile CNN models. In particular, the present disclosure provides systems and methods to perform neural architecture search using a novel factorized hierarchical search space that permits layer diversity throughout the network, thereby striking the right balance between flexibility and search space size. The resulting neural architectures are able to be run relatively faster and using relatively fewer computing resources (e.g., less processing power, less memory usage, less power consumption, etc.), all while remaining competitive with or even exceeding the performance (e.g., accuracy) of current state-of-the-art mobile-optimized models.

Abstract: The disclosure provides technology for importing a set of media items from a content source by optically analyzing a graphical interface of the content source. An example method includes initiating, by a processing device, an import of a set of media items from a content source; capturing image content of a graphical interface of the content source; extracting data from the image content of the graphical interface; identifying a media item of the content source based on the data from the image content; and storing a reference to the media item.

Abstract: A method for configuring and deploying execution environments for software applications includes receiving a bootstrap execution environment from a data store, the bootstrap execution environment including a software application, the software application including a manifest of dependencies. The method includes executing the bootstrap execution environment and determining whether an enhanced execution environment is available from the data store. When the enhanced execution environment is available from the data store, the method includes receiving the enhanced execution environment from the data store and enhancing the bootstrap execution environment based on the received enhanced execution environment. When the enhanced execution environment is not available from the data, the method includes enhancing the bootstrap execution environment based on the manifest of dependencies to create the enhanced execution environment and storing the enhanced execution environment in the data store.

Abstract: This document describes techniques and systems that enable grid-based enrollment for face authentication. The techniques and systems include overlaying a three-dimensional (3D) tracking window over a preview image of the user's face displayed via a display device. The 3D tracking window includes a plurality of segments, which persist to correspond to an approximate direction that the user's face is facing. Based on the tracking, segments are highlighted to indicate the approximate direction that the user's face is facing, a camera captures enrollment images of the user's face facing that direction, and embeddings are generated based on the enrollment images and stored in a fixed grid of pose cells corresponding to various facial poses for use in face authentication. Responsive to generation and storage of the embeddings, an indication that the one or more segments are completed is provided.

Abstract: A method for evaluating a verification model includes receiving a first and a second set of verification results where each verification result indicates whether a primary model or an alternative model verifies an identity of a user as a registered user. The method further includes identifying each verification result in the first and second sets that includes a performance metric. The method also includes determining a first score of the primary model based on a number of the verification results identified in the first set that includes the performance metric and determining a second score of the alternative model based on a number of the verification results identified in the second set that includes the performance metric. The method further includes determining whether a verification capability of the alternative model is better than a verification capability of the primary model based on the first score and the second score.

Abstract: The various implementations described herein include a video camera assembly that includes: (1) a housing; (2) an image sensor encased in the housing and configured to capture activity of the smart home environment; (3) a wireless radio configured to transmit video frames captured by the image sensor to an electronic device via a remote server; (4) at least one infrared transmitter configured to selectively illuminate the smart home environment; (5) one or more circuit boards encased in the housing, the one or more circuit boards including at least one processor mounted thereon; and (6) a heating component coupled to the image sensor, the heating component configured to continuously maintain the image sensor at a temperature above a threshold temperature while the image sensor is capturing the activity of the smart home environment.

Abstract: A user interface comprising a set of comments that are aggregated from and included in a plurality of collaborative documents provided by a cloud-based content management platform are displayed. Each of the plurality of collaborative documents is a separate data file. A modification to a comment of the set of comments is received based on user input via the user interface displaying the set of comments included in the plurality of collaborative documents. Responsive to receiving the modification to the comment of the set of comments based on the user input via the user interface displaying the set of comments included in the plurality of collaborative documents, the user interface is updated to reflect the modified comment of the set of comments.

Abstract: Implementations set forth herein relate to providing selectable autofill suggestions, which correspond to application actions that are at least partially fulfilled using server command data—prior to a user selecting a particular selectable autofill suggestion. Proactively fulfilling command data in this way mitigates latency between user selection of a suggestion and fulfillment of a particular action. Initially, a partial input can be processed to generate autofill suggestions, which can be communicated to a server device for further processing. The autofill suggestions can also be rendered for selection at a touch display interface, thereby allowing a user to select one of the autofill suggestions. As command fulfillment data is provided by the server, the command fulfillment data can be available to a corresponding application(s) in order that any corresponding actions can be at least partially fulfilled prior to user selection.

Abstract: Aspects of the disclosure relate to providing a secure collaboration between one or more PCIe accelerators and an enclave. An example system may include a PCIe accelerator apparatus. The PCIs accelerator apparatus may include the one or more PCIe accelerators and a microcontroller configured to provide a cryptographic identity to the PCIe accelerator apparatus. The PCIe accelerator apparatus may be configured to use the cryptographic identity to establish communication between the PCIe accelerator apparatus the enclave.