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

Abstract: A process adapts user-initiated search queries. The process executes at a client device with a microphone. The process downloads audio fingerprints from a remote server for a plurality of video programs, and downloads information that correlates the audio fingerprint to the video programs. The audio fingerprints are preselected according to relevancy criteria, including stored user preferences and prior search queries by the user. The audio fingerprints and correlating information are stored locally. The process detects ambient sound using the microphone and computes one or more sample audio fingerprints from the detected ambient sound. The process matches a sample audio fingerprint to a locally stored audio fingerprint and uses the correlating information to identify a first video program corresponding to the matched sample audio fingerprint. The process then receives user input to initiate a search query. The process provides auto-complete suggestions for the search query based on the first video program.

Abstract: A quantum neural network architecture. In one aspect, a quantum neural network trained to perform a machine learning task includes: an input quantum neural network layer comprising (i) multiple qubits prepared in an initial quantum state encoding a machine learning task data input, and (ii) a target qubit; a sequence of intermediate quantum neural network layers, each intermediate quantum neural network layer comprising multiple quantum logic gates that operate on the multiple qubits and target qubit; and an output quantum neural network layer comprising a measurement quantum gate that operates on the target qubit and provides as output data representing a solution to the machine learning task.

Abstract: This disclosure describes apparatuses and techniques for a switched multi-cell battery system for electronic devices. In some aspects, a switched multi-cell battery system may transfer, via a plurality of power control switches electrical power from a power adapter to components of the electronic device by charging battery cells in series and by discharging the battery cells in parallel or as a single battery cell. As a result, the switched multi-cell battery system may reduce or eliminate a voltage step-down conversion stage to increase a power-transfer efficiency of an electronic device. By doing so, charging times may be reduced or operating times may be increased, thereby improving users' experience with their electronic devices.

Abstract: A learning model is trained for rate-distortion behavior prediction against a corpus of a video hosting platform and used to determine optimal bitrate allocations for video data given video content complexity across the corpus of the video hosting platform. Complexity features of the video data are processed using the learning model to determine a rate-distortion cluster prediction for the video data, and transcoding parameters for transcoding the video data are selected based on that prediction. The rate-distortion clusters are modeled during the training of the learning model, such as based on rate-distortion curves of video data of the corpus of the video hosting platform and based on classifications of such video data. This approach minimizes total corpus egress and/or storage while further maintaining uniformity in the delivered quality of videos by the video hosting platform.

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: 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 are directed to enabling a representative associated with an entity to quickly and efficiently modify a voice bot associated with the entity. The voice bot can be previously trained to communicate with user(s) on behalf of the entity through various communication channels (e.g., a telephone communication channel, a software application communication channel, a messaging communication channel, etc.). Processor(s) of a computing device can receive, from the representative, representative input to modify behavior(s) and/or parameter(s) that the voice bot utilizes in communicating with the plurality of users via the communication channels, determine whether the representative is authorized to cause the behavior(s) and/or parameter(s) to be modified, and cause the behavior(s) and/or parameter(s) to be modified in response to determining that the representative is authorized.

Abstract: According to an aspect, a method of restoring a computing session includes receiving, over a network, session data from a server computer, where the session data includes information about at least one session item that is active during a computing session of a first computing device. The at least one session item includes at least one of a web application or a native application. The method includes restoring the at least one session item of the computing session on a second computing device based on the session data, where the at least one session item is arranged on a user interface of the second computing device according to a display arrangement that corresponds to a display arrangement of the at least one session item on a user interface of the first computing device.

Abstract: Implementations set forth herein relate to an automated assistant that facilitates the creation of complex messages from user input(s) to the automated assistant. Each message can be created according to a respective template that is selected based on user input that directs the automated assistant to communicate a message to a recipient. Furthermore, sections of a template can be designated for certain content based on prior messages communicated by one or more users to one or more recipients. In this way, in response to a user requesting that the automated assistant send a message, the automated assistant can select a related template and fill out the template accordingly. In some instances, content that is assigned to certain sections of the selected template can come from a variety of different sources and/or may not be explicitly specified in the request from the user to the automated assistant.

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.

Abstract: Methods, systems, and apparatus for controlling smart devices are described. In one aspect a method includes receiving image data for an image captured by a camera of a mobile device of a user and determining that the image depicts at least one of a smart device or a physical control for the smart device. In response to determining that that the image depicts a smart device or a physical control for the smart device, identifying one or more user interface controls for controlling the smart device, and generating and presenting, at a display of the mobile device, the one or more user interface controls for controlling the smart device. The method can further include detecting, at the display of the mobile device, user interaction with at least one of the one or more user interface controls, and controlling the smart device based on the detected user interaction.

Abstract: An electronic device stores a voice assistant library for execution on the electronic device based on the electronic device having a first device type. The electronic device receives a verbal input from a user. It extracts request information from the verbal input by processing the verbal input using the voice assistant library executing on the device. It transmits a request to a remote system. The electronic device receives a response to the request. The response is generated by the remote system. The electronic device performs an operation in accordance with the response by one or more voice-processing modules of the configured voice assistant library.

Abstract: The technology relates to allowing a user to enter text into text boxes using a stylus. For instance, first user input identifying a text box displayed on a display of the computing device may be received. Based on the received first user input, a handwriting field may be generated on the display without visual impact on the display. A second user input within the handwriting field may be received. The second user input may be converted into typed text, and the typed text may be displayed in the text box.

Abstract: A device includes: a substrate; a superconducting quantum interference device (SQUID) including a superconductor trace arranged on an upper surface of the substrate and having at least one Josephson junction interrupting a path of the superconductor trace, in which the superconductor trace includes a first superconductor material that exhibits superconducting properties at or below a corresponding superconducting critical temperature; and a dielectric capping layer on an upper surface of the SQUID, in which the dielectric capping layer covers a majority of the superconductor trace of the SQUID, and the capping layer includes an opening through which a first region of the SQUID is exposed, the first region of the SQUID including a first Josephson junction.

Abstract: Methods, systems, and apparatus, including computer-readable media, are described for a hardware circuit configured to implement a neural network. The circuit includes a first memory, respective first and second processor cores, and a shared memory. The first memory provides data for performing computations to generate an output for a neural network layer. Each of the first and second cores include a vector memory for storing vector values derived from the data provided by the first memory. The shared memory is disposed generally intermediate the first memory and at least one core and includes: i) a direct memory access (DMA) data path configured to route data between the shared memory and the respective vector memories of the first and second cores and ii) a load-store data path configured to route data between the shared memory and respective vector registers of the first and second cores.

Abstract: This document describes a passive adapter for wireless charging of an electronic device and associated methods and systems. The described passive adapter includes two coils connected by a capacitor and separated by a core material that prevents mutual coupling between the coils. These two coils may have differing sizes, such that one coil can size-match to a transmitter coil of an existing wireless charger and the second coil can size-match to a smaller (or larger) receiver coil in a wireless-power receiver to charge a battery of the wireless-power receiver. In aspects, these two coils may be separated by a distance that enables the passive adapter to act as a passive repeater by bridging a space between the transmitter coil and the receiver coil.

Abstract: Systems and methods for generating social annotations for content that are capable of being seen by a broad audience are provided herein. A system can include a user identification component configured to identify a user that has potential for generating a valuable endorsement of a content item based at least in part on a sharing setting associated with a user. The system further includes an audience component configured to determine an audience associated with the user based at least in part on the sharing setting, a user selection component configured to select the user as a candidate user for generating the endorsement of the content item in response to a determination that a size of the audience exceeds a threshold, and a targeted content component configured to, in response to selection of the user, provide the content item to the user with a capability to endorse the content item.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses a set of speech recognition hypothesis samples, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.