Abstract: Techniques for implementing instance local boots in a cloud provider network via auxiliary domains are described. An auxiliary compute instance is launched and attached to a local storage device of the computing device. The auxiliary compute instance can pre-warm a boot volume by fetching its data from a remote system and storing the boot volume to the local storage device. The auxiliary compute instance is terminated, and a user compute device is launched into the same slot and connected to the local storage device. The user compute device utilizes the pre-warmed boot volume for launch.

Abstract: Systems and methods are disclosed for automated container stacking stations. In one embodiment, an example system may include a housing having a first side and a second side, a lifting component configured to lift a first container from a first position to a second position, and to lower the first container from the second position to a third position, such that the first container is stacked on a second container, and a container centering component having a first container engagement member and a second container engagement member, the container centering component configured to align the first container in a predetermined position.

Abstract: Described herein is a system for encoding audio watermarks with frequency extensions to enable enhanced watermark detection. An extended audio watermark may include an existing audio watermark and a duplicate audio watermark, enabling backwards compatibility with existing watermark detection while also enabling enhanced watermark detection with increased accuracy. For example, embedding the extended audio watermark enables (i) limited devices to perform watermark detection to detect the existing audio watermark, and (ii) improved devices to perform enhanced watermark detection to detect the extended audio watermark. As the extended audio watermark includes redundancy in the form of duplicate audio watermark(s), an accuracy of performing enhanced watermark detection is increased relative to detecting the existing audio watermark alone.

Abstract: A post-task-completion retention period for which a computing resource is to be retained, without de-activating the resource, on behalf of a set of requesters of machine learning tasks is determined at a machine learning service. A first task, identified at the service prior to expiration of the retention period at a first computing resource at which a second task has completed, is initiated at the first computing resource. In response to obtaining an indication of a third task and determining that a threshold criterion associated with the retention period satisfies a criterion, the third task is initiated at an additional computing resource. The additional computing resource is de-activated after the third task completes, without waiting for the retention period to expire.

Abstract: Technologies directed to interleaved phased array antennas are described. One apparatus includes a support structure, a first phased array antenna, and a second phased array antenna. The first array antenna includes a first set of antenna elements disposed on a surface of the support structure. The first set of antenna elements is located within a perimeter of a first circular area. The second antenna includes a second set of antenna elements. The second set of antenna elements is located within a perimeter of a second circular area. The second circular area partially overlaps the first circular area. The majority of the second set of antenna elements are located outside the perimeter of the first circular area. A majority of the second set of antenna elements are located in the second circular area in the area not overlapped by the first circular area.

Abstract: Techniques for at least the generation of a chatbot built from a custom vocabulary and to use runtime hints during inference are described. In some examples, the generation of the chatbot includes receiving a request to build a chatbot using a bot definition and a custom vocabulary, wherein the chatbot is to use runtime hints during usage; building the chatbot from the bot definition and custom vocabulary by at least: generating automatic speech recognition (ASR) artifacts to be used in decoding audio input into the chatbot into text for at least one other component of the chatbot to use in determining a next act to be performed, the ASR artifacts including artifacts that use the custom vocabulary and artifacts that do not use the custom vocabulary, and storing the ASR artifacts.

Abstract: Some embodiments provide a method for training a machine-trained (MT) network that processes inputs using network parameters. The method propagates a set of input training items through the MT network to generate a set of output values. The set of input training items comprises multiple training items for each of multiple categories. The method identifies multiple training item groupings in the set of input training items. Each grouping includes at least two training items in a first category and at least one training item in a second category. The method calculates a value of a loss function as a summation of individual loss functions for each of the identified training item groupings. The individual loss function for each particular training item grouping is based on the output values for the training items of the grouping. The method trains the network parameters using the calculated loss function value.

Abstract: Disclosed are various embodiments for interfaces for creating radio-based private networks. In one embodiment, a request is received via an interface to create a radio-based private network for a customer. The request indicates a quantity of wireless devices that will connect to the radio-based private network. A quantity of radio units to serve the radio-based private network is determined based at least in part on the quantity of wireless devices. The radio units are preconfigured to implement a radio access network for the radio-based private network. A shipment is initiated to the customer of the radio units that have been preconfigured. Resources in a cloud provider network are provisioned to function as a core network for the radio-based private network.

Abstract: Users propose, review, reject, comment on, and approve rules or program code to implement rules in a decentralized network. When the users act on proposed rules, they are credited with member scores according to their contributions. The rules are used to calculate, for example, obligations for a user. When the network is used to calculate a result, the use of the rules for calculating the result are used to determine a score for the users who contributed to the rules.

Abstract: Techniques for determining a command or intent likely to be subsequently invoked by a user of a system are described. A user inputs a command (either via a spoken utterance or textual input) to a system. The system determines content responsive to the command. The system also determines a second command or corresponding intent likely to be invoked by the user subsequent to the previous command. Such determination may involve analyzing pairs of intents, with each pair being associated with a probability that one intent of the pair will be invoked by a user subsequent to a second intent of the pair. The system then outputs first content responsive to the first command and second content soliciting the user as to whether the system to execute the second command.

Abstract: A system configured to perform adaptive active noise cancellation (ANC) processing. Specifically, the system may adaptively determine a feed-forward ANC filter by maximizing a ratio of A:B, where A corresponds to microphone-ear coherence and B corresponds to microphone-microphone coherence between the feed-forward microphones. By maximizing this ratio, the system may determine weighted gain values used to combine the feed-forward microphone signals. In addition, the system may (i) apply a fixed feed-forward ANC filter profile selected based on a geometry of the device and a generalized ear response, (ii) monitor a secondary path to select from a plurality of feed-forward ANC filter profiles based on an individual user's ear response, or (iii) adaptively update the feed-forward ANC filter based on a feedback microphone signal.

Abstract: Disclosed are various embodiments for scheduling use of heterogeneous frequency schemes for radio-based networks. In one embodiment, a first frequency scheme is selected instead of a second frequency scheme based at least in part on the first frequency scheme being capable of meeting a quality-of-service requirement associated with a wireless device or an application executed in the wireless device. A radio-based network is configured to provide service to the wireless device in a geographic area using the first frequency scheme instead of the second frequency scheme.

Abstract: This disclosure describes a system for disambiguating between multiple potential users that may have performed an item action (e.g., item removal or item placement) at an inventory location. For example, if there are three picking agents (users) standing near an inventory location and one of the agents removes an item (item action) from the inventory location, the example systems and processes described herein may utilize various inputs to disambiguate between the users and determine which of the potential users performed the item action.

Abstract: A system is provided for modifying how an output is presented via a multi-device synchronous configuration based on detecting a speech characteristic in the user input. For example, if the user whispers a request, then the system may temporarily modify how the responsive output is presented to the user via multiple devices. In one example, the system may lower the volume on all devices presented the output. In another example, the system may present the output via a single device rather than multiple devices. The system may also determine to operate in an alternate output mode based on certain non-audio data.

Abstract: Systems and methods are described for recommending pairs or sets of clothing items for an individual to wear together, including learning a compatibility metric personalized to each individual. A framework is used to learn compatibility that is personalized to the user based on initial item feedback that may be received from the user via user interfaces that prompt the user to indicate whether the user would wear certain clothing items together and/or individually.

Abstract: A system and method for temporarily disabling keyword detection to avoid detection of machine-generated keywords. A local device may operate two keyword detectors. The first keyword detector operates on input audio data received by a microphone to capture keywords uttered by a user. In these instances, the keyword may be detected by the first detector and the audio data may be indicated for speech processing. The system may determine output audio data responsive to the input audio data. The local device may process the output audio data to determine that it also includes the keyword. The device may then disable the first keyword detector while the output audio data is played back by an audio speaker of the local device. Thus the local device may avoid detection of a keyword originating from the output audio. The first keyword detector may be reactivated after a time interval during which the keyword might be detectable in the output audio.

Abstract: A vehicle signal relay system enables a relay agent in a first zone of a vehicle to send sensor signals having a first link-layer communication protocol to a software application deployed on a compute unit in another zone of the vehicle that is connected using another link-layer communication protocol. The vehicle signal relay system allows the software application to identify target relay agents with access to needed sensor signals. The vehicle signal relay system may further enable one way or mutual attestation. The vehicle signal relay system may also allow filters to be applied to the subscribed vehicle sensor signals, and may allow the software application to determine a communication protocol to be used between the software application and the relay agent.

Abstract: A sensor head transitions between a retracted and extended state. While retracted, sensors are covered. While extended, the sensors are exposed and may be used to acquire sensor data about the physical space. A force applied by a user, or a received command, may initiate transition. For example, a user may press on the sensor head to initiate retraction or extension. A motor provides a force to move the sensor head and generate haptic feedback, while a position encoder determines a displacement of the sensor head due to an external force being applied. Different applications of force by the user to the sensor head may result in different operations by the device. For example, a short push may retract the sensor head and disable the sensors for a specified time interval. In comparison a long push may retract the sensor head and disable the sensors until a specified clock time.

Abstract: Techniques for ontology linking of unstructured text as a service are described. A service may receive a request to link unstructured text to a standardized ontology, and the service may segment and tokenize the unstructured text and send the result to multiple services implementing multiple deep machine learning models trained to identify particular entities and one or more relationships between entities. The service may perform a search of the standardized ontology to identify a set of similar candidates from the standardized ontology for the detected entities and the one or more relationships, and then rank the set of similar candidates from the standardized ontology according to their similarity to the detected entities within the unstructured text. The output from the service may include a result identifying a highest ranked candidate of the set of similar candidates from the standardized ontology for the detected entities within the unstructured text.

Abstract: Systems and methods are disclosed for wheel wear monitoring systems for shuttles powered by linear synchronous motors. An example system may include a first rail segment that forms a first side of the track, the first rail segment having a first aperture, a second rail segment that forms a second side of the track, the second rail segment having a second aperture, and a first camera disposed adjacent to the first aperture. The system may include a second camera disposed adjacent to the second aperture, and a controller configured to determine a first set of images of a first wheel of the shuttle using the first camera, determine a second set of images of a second wheel of the shuttle using the second camera, and determine a wear status of the first wheel based at least in part on the first set of images.