Abstract: An NLQ-SQLQ tool or service of a provider network may receive a natural language query (NLQ) from a client and convert the NLQ to an SQL query using ontological codes and placeholders. For one or more portions of the NLQ, the tool/service determines that the portion is associated with one or more codes of an ontology. The tool/service then assigns, based on criteria, a particular code to the portion. The tool/service replaces portions of the NLQ with different argument placeholders to generate a modified NLQ. A trained model converts the modified NLQ into an initial SQL query that has argument placeholders and subquery placeholders. The tool/service generates a final SQL query based on the initial SQL query, predefined SQL subquery templates associated with the subquery placeholders, and codes associated with the argument placeholders. The tool/service executes the final SQL query and sends results to the client.

Abstract: A virtual network verification service for provider networks that leverages a declarative logic programming language to allow clients to pose queries about their virtual networks as constraint problems; the queries may be resolved using a constraint solver engine. Semantics and logic for networking primitives of virtual networks in the provider network environment may be encoded as a set of rules according to the logic programming language; networking security standards and/or client-defined rules may also be encoded in the rules. A description of a virtual network may be obtained and encoded. A constraint problem expressed by a query may then be resolved for the encoded description according to the encoded rules using the constraint solver engine; the results may be provided to the client.

Abstract: Hyperparameters for tuning a machine learning system may be optimized using Bayesian optimization with constraints. The hyperparameter optimization may be performed for a received training set and received constraints. Respective probabilistic models for the machine learning system and constraint functions may be initialized, then hyperparameter optimization may include iteratively identifying respective values for hyperparameters using analysis of the respective models performed using an acquisition function implementing entropy search on the respective models, training the machine learning system using the identified values to determine measures of accuracy and constraint metrics, and updating the respective models using the determined measures.

Abstract: A system for storing data includes a rack, one or more data storage modules coupled to the rack, and one or more data control modules coupled to the rack. The data storage modules may include a chassis, two or more backplanes coupled to the chassis, and one or more mass storage devices (for example, hard disk drives) coupled to the backplanes. The data control modules may access the mass storage devices in the data storage modules.

Abstract: Generally described, one or more aspects of the present application relate to prefetching container image layers for use in a cluster of compute instances. For example, the dependencies among the individual layers within the container images stored and/or executed on a cloud provider network may be analyzed. Then, the layers that are likely to be used by a user of the cloud provider network may be identified and prefetched into the caches of the compute instances provided by the cloud provider network, before execution of the container images including such layers is requested by the user. By doing so, the latency between the time a request to execute a set of container images is received and the time the execution of the set of container images is actually initiated can be reduced, thereby providing an improved and more efficient application execution experience to the user.

Abstract: Some embodiments provide a neural network inference circuit (NNIC) for executing a neural network that includes multiple computation nodes at multiple layers. The NNIC includes a set of clusters of core computation circuits and a channel, connecting the core computation circuits, that includes separate segments corresponding to each of the clusters. The NNIC includes a fabric controller circuit, a cluster controller circuit for each of the clusters, and a core controller circuit for each of the core computation circuits. The fabric controller circuit receives high-level neural network instructions from a microprocessor and parses the high-level neural network instructions.

Abstract: A system includes access controls that allow or deny a request based at least in part on a context associated with the request. A service receives a request from a client, and forwards information that describes the request and the context of the request to a context management service. The context management service determines whether the request should be allowed by querying a set of context validation plugins. Each context validation plugin analyzes particular characteristics of a request's context, and based at least in part on the request's context, indicates to the context management service that the request should be allowed or denied. If a quorum of the context validation plugins indicate to the context management service that the request should be allowed, the context management service indicates to the service that the request is allowed within the provided context.

Abstract: Techniques for anomaly and causality detection are described. An example includes receiving time series data; performing anomaly detection on the received time series data to detect at least one anomaly using an anomaly detection model; detecting a causal relationship between measures, wherein a set of measures are related when a first of the set of measures has a causal influence on a second of the set of measures, wherein a single time series is a metric and a measure is a numerical or categorical quantity a metric describes; and outputting a result of the anomaly and causality relationship detections.

Abstract: Described herein is a computer-implemented method for extracting and identifying an audio song. An audio file can be accessed by a computing device. A set of audio categories and a set of probabilities associated with the set of audio categories can be determined for a first audio clip. A subset of the set of audio categories can be determined based on a subset of the set of probabilities. Each audio category of the subset of the set of audio categories can correspond to an audio class label. Whether the first audio clip is part of a song can be determined. The song can be defined by combining the first audio clip with other audio clips.

Abstract: Devices and methods for routing content are provided herein. In some embodiments, a method for routing content include receiving audio data representing a command from a first electronic device, determining content that is associated with the command, sending responsive audio data to the first electronic device, and sending instructions to the second electronic device to output the content associated with the command. In some embodiments, a method for routing contents includes determining a state of the second electronic device and sending instructions to output the content to a selected one of the first and second electronic devices based on the state of the second electronic device.

Abstract: Single use cartridges for testing biological samples are provided that include multiple processing channels. A single use cartridge includes an aliquot staging well, a first amplification well, a second amplification well, an actuation port, and a fluid channel control valve assembly. The fluid channel control valve assembly is reconfigurable between a first fluid channel configuration and a second fluid channel configuration.

Abstract: A system responds to a request to enable a restoration capability for a first database instance of a first operating environment. The system stores, in the first operating environment, transaction data for the first database instance and data indicative of aspects of the configuration of the first operating environment on which the first database instance is dependent. The transaction data and configuration data are replicated to a second environment. In response to a request to restore the first database instance, a second operating environment is configured according to the replicated configuration data, and the data is restored to a second database instance, in the second operating environment, based on the replicated transaction data.

Abstract: Techniques for capturing spoken user inputs while a device is prevented from capturing such spoken user inputs are described. When a first device becomes incapable of capturing spoken user inputs intended for a system, a second device, for capturing such spoken user inputs, may be identified. The second device may be identified based on the second device being connected to a same vehicle computing system as the first device. The second device may be enabled to capture spoken user inputs, intended for the system, until the first device is again able to capture such spoken user inputs.

Abstract: Techniques for distributing data associated with the weight values of a neural network model are described. The techniques can include performing computations associated with the neural network model in a neural network accelerator to generate data associated with weights of the neural network model. A multicast request packet is then generated to distribute the data. The multicast request packet may contain the data associated with the weights, and an address in a multicast address range of a peripheral bus multicast switch. The multicast request packet is sent to a port of the peripheral bus multicast switch, and in response, the peripheral bus multicast switch generates multiple packets containing the data from the multicast request packet and forwards them to multiple peripheral bus ports corresponding to other processing nodes of the system.

Abstract: Techniques and methods are disclosed for detecting long-form audio content in one or more audio files. A computing system receives first audio data corresponding to a first version of an audio file and second audio data corresponding to a second version of the audio file. The computing system generates a first transcript of the first audio data and a second transcript of the second audio data. The computing system compares the first audio data and the second audio data and the first transcript and the second transcript to identify advertisement portions and content portions of the audio data. Using a semantic model based on a machine learning (ML) transformer, the computing system can determine advertisement segments within the advertisement portions, the advertisement segments corresponding to separate advertisements. Information corresponding to the duration and location of the advertisement segments is stored in a data store of the computing system.

Abstract: Systems and methods for preemptive wakeword detection are disclosed. For example, a first part of a wakeword is detected from audio data representing a user utterance. When this occurs, on-device speech processing is initiated prior to when the entire wakeword is detected. When the entire wakeword is detected, results from the on-device speech processing and/or the audio data is sent to a speech processing system to determine a responsive action to be performed by the device. When the entire wakeword is not detected, on-device processing is canceled and the device refrains from sending the audio data to the speech processing system.

Abstract: A monitoring service analyzes client-based monitoring data in correlation with network-based monitoring data for paths between two endpoints in a network upon request from a client. The endpoint can be any valid private IP address or DNS name where traffic is to be sent. Clients may define parameters for the monitoring, including thresholds for identifying network issues based on the client-based monitoring data. Different levels of network-based monitoring may be performed responsive to results of the correlation and continued performance determinations relative to the thresholds. The client-based and network-based monitoring data may include reports of performance signals, such as packet loss and round-trip time or other measured latency, as well as events such as connection issues and timeouts. The monitoring data from the different sources can be compared to determine whether a network issue is present in the network or outside of the network/in the client.

Abstract: A technology is described for device communication with computing regions. An example method may include receiving at a first computing region a request for a computing resource. In response to receiving the request, a device associated with the request may be authenticated using authentication credentials for the device. An identity token that indicates permission for the device to access the computing resource in a second computing region may be generated and the identity token and instructions to connect to the second computing region may be provided to the device. The device may present the identity token to the second computing region in order to access the computing resource in the second computing region.

Abstract: Methods, systems, and computer-readable media for delivery of log records to stateless clients are disclosed. A record delivery system receives, from a client, a first request to read from a persistent log comprising an ordered sequence of records. The first request is associated with a receiver session. The system sends a first set of records to the client and stores a data structure indicating that the first set of records was sent to the client in the receiver session. The system receives, from the client, a second request to read from the persistent log in the receiver session. Based at least in part on the data structure, the system determines a second set of one or more records in the persistent log. The system sends the second set of records to the client.

Abstract: Enhanced training data representative of possible inputs is used to train a machine learning system. For example, a machine learning system to determine identity based on an image of a human palm may be trained using enhanced training data comprising images. The enhanced training data may comprise source images that have been modified to appear to depict synthetic artifacts that attempt to simulate human palms, augmented images of dirty hands, and so forth. A synthetic artifact image may be produced by selectively removing some data from a source image. An augmented image may be produced by selectively blending the source image with features extracted from sample images. These images may then be used as training data to train the machine learning system.