Abstract: Apparatuses, systems, and techniques are presented to generate recommendations for players of a game. In at least one embodiment, one or more neural networks are used to generate one or more recommendations for one or more players of a game based, at least in part, upon one or more cumulative changes of state in the game.

Abstract: A mobile device supports positioning with positioning reference signals (PRS) on multiple beam by dividing the PRS processing into two separate modes, an acquisition mode and a tracking mode. In acquisition mode, the mobile device performs a fast scan of all of the beams from a base station transmitting PRS using less than the full set of resources for the PRS, i.e., less than the full bandwidth and/or less than the full number of repetitions of the PRS. The mobile device may select the best beams to use for positioning, e.g., based on signal strength metric. In tracking mode, the mobile device tracks the PRS from only the selected beams using the full set of resources for the PRS. The mobile device may return to acquisition mode after a predetermined number of positioning occasions or if the selected beams are no longer valid due to movement or change in conditions.

Abstract: Apparatuses, systems, and techniques are presented to generate animation. In at least one embodiment, one or more neural networks are used to generate one or more animation representations of one or more textual characters, wherein the one or more animation representations of the one or more textual characters are to be stored and reused to represent the one or more animation representations of the one or more textual characters.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for surfacing content related to electronic calendar events are presented. An electronic calendar event library may be maintained. One or more calendar events that meet threshold time criteria in relation to a current time may be identified. One or more rules may be applied to the identified events to determine whether contextual information and/or actions should be surfaced in relation to those events. In some examples, an event priority score may be calculated for each of the identified events. Contextual information and/or actions associated with events with event priority scores that exceed a threshold value may be surfaced. The contextual information and/or actions may be prioritized based on the event priority scores.

Abstract: Apparatuses, systems, and techniques are presented to select segments of content. In at least one embodiment, one or more neural networks are used to select one or more video segments from one or more video files based at least in part upon an indication of one or more emotions, of one or more viewers of the one or more video segments, during presentation of the one or more video segments.

Abstract: Apparatuses, systems, and techniques are presented to determine reactions to content of one or more users. In at least one embodiment, one or more neural networks can predict one or more reactions from one or more content viewers based, at least in part, on one or more images contained in the content.

Abstract: A method and a system for transporting inventory in a storage facility is provided. The system includes an inventory storage unit (ISU) and a transport vehicle. The ISU includes a base shelf, and a plurality of support plates mounted below the base shelf. The transport vehicle includes a top plate and a control device that controls movement of the top plate. Upon actuation of an interlocking mechanism of the transport vehicle that is aligned beneath the ISU, the top plate is lifted to a first height and then rotated for engaging the top plate with the support plates of the ISU. The engaged top plate is further lifted to a second height to lift the ISU off the work floor of a storage facility. Upon lifting the ISU, the transport vehicle transports the ISU to another location in the storage facility.

Abstract: Apparatuses, systems, and techniques are presented to determine whether to render one or more content objects. In at least one embodiment, one or more neural networks can determine whether to render an object to be transmitted in media content based at least in part upon whether those objects were previously rendered for that content.

Abstract: Apparatuses, systems, and techniques are presented to determine actions to be taken for data anomalies. In at least one embodiment, audio and video data captured for an environment of a user can be analyzed to detect one or more data anomalies and determine whether to notify this user depending on whether the anomalies are applicable to this user.

Abstract: The present invention relates to a battery-powered wireless charging station for charging an electronic device, and including a wireless charging station sensor configured to detect a predetermined spatial relationship between a wireless charge receiving system of the electronic device and a wireless charge providing system of the wireless charging station.

Abstract: Apparatuses, systems, and techniques to facilitate understanding of media content using neural networks to adjust playback speed and volume based on environmental and other factors. In at least one embodiment, playback of media content is slowed down or sped up if audio associated with said media content is difficult to understand based on background noise, accent, difficulty of material, as well as other factors that decrease understandability of media content.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning using agent curricula. One of the methods includes maintaining data specifying plurality of candidate agent policy neural networks; initializing mixing data that assigns a respective weight to each of the candidate agent policy neural networks; training the candidate agent policy neural networks using a reinforcement learning technique to generate combined action selection policies that result in improved performance on a reinforcement learning task; and during the training, repeatedly adjusting the weights in the mixing data to favor higher-performing candidate agent policy neural networks.

Abstract: Embodiments of the present disclosure provide methods, systems, apparatuses, and computer program products that provide for an improved and more efficient system for transmitting content to client devices. The embodiments disclose an apparatus that clusters user behavior based on platform session records. The platform session records comprise stored data associated with a plurality of user inputs received by the system for the duration of a platform session. The apparatus and methods transform the platform session records into data comprising a form that is usable for identifying clusters of platform sessions. As a result of the clustering methodologies, the apparatus is configured to deliver content specifically optimized for users of client devices. The present disclosure thus provides for an improved networked system that reduces the amount of data transferred via the network and allows for a more efficient system that has reduced infrastructure requirements and improved performance.

Abstract: Apparatuses, systems, and techniques to detect cheating, manipulation, or unfair advantages. In at least one embodiment, cheating is determined using a reconstruction probability inferred, using one or more neural networks, for video data for a player of a game.

Abstract: Apparatuses, systems, and techniques are presented for generating instructional text. In at least one embodiment, an instructional video is analyzed to determine logical steps of a process or task demonstrated in that video, and instructive text is generated for those logical steps.

Abstract: A voltage supervisor includes a first transistor coupled between a first supply voltage and a second supply voltage. The voltage supervisor includes a second transistor coupled between the first supply voltage and the second supply voltage. The voltage supervisor is configured to provide a first current proportional to a difference in gate-to-source voltages of the first transistor and the second transistor. The voltage supervisor is also configured to provide a second current proportional to a difference in the first supply voltage and the difference in gate-to-source voltages of the first transistor and the second transistor. The voltage supervisor is configured to compare the first current to the second current to determine a voltage value that changes a state responsive to the first supply voltage crossing a threshold.

Abstract: A method and a system for transporting inventory in a storage facility is provided. The system includes an inventory storage unit (ISU) and a transport vehicle. The ISU includes a base shelf, and a plurality of support plates mounted below the base shelf. The transport vehicle includes a top plate and a control device that controls movement of the top plate. Upon actuation of an interlocking mechanism of the transport vehicle that is aligned beneath the ISU, the top plate is lifted to a first height and then rotated for engaging the top plate with the support plates of the ISU. The engaged top plate is further lifted to a second height to lift the ISU off the work floor of a storage facility. Upon lifting the ISU, the transport vehicle transports the ISU to another location in the storage facility.

Abstract: A system and method for determining a location of a client device is described herein. In particular, a client device receives images captured by a camera at the client device. The client device identifies features in the images. The features may be line junctions, lines, curves, or any other features found in images. The client device retrieves a 3D map of the environment from the map database and compares the identified features to the 3D map of the environment, which includes map features such as map line junctions, map lines, map curves, and the like. The client device identifies a correspondence between the features identified from the images and the map features and determines a location of the client device in the real world based on the correspondence. The client device may display visual data representing a location in a virtual world corresponding to the location in the real world.

Abstract: A circuit includes a reference voltage generator circuit and a regulation loop circuit having an output voltage terminal. The regulator circuit further includes a fault detection circuit having a first input terminal coupled to the output voltage regulator terminal of the regulation loop circuit. The fault detection circuit asserts, on an output terminal of the fault detection circuit, a fault flag signal responsive to a voltage on the first input terminal falling below a first threshold. A programmable filter is coupled between the reference voltage generator circuit and the regulation loop circuit and is coupled to the fault detection circuit. The programmable filter has a programmable time constant. The programmable filter responds to an assertion of the fault flag signal by decreasing the time constant.