Abstract: Technology embodied in a computer-implemented method for receiving a multi-modal input representing a query associated with a physical object, processing the multi-modal input to identify the physical object, and determining, based in part on an identification of the physical object and by accessing a language processing model, at least one response to the query associated with the physical object. The method also includes determining a sequence of actions associated with the at least one response, the sequence including at least one action that involves an interaction with at least one portion of the physical object. The method further includes generating a digital representation of the at least one action, and providing the digital representation to a user-device for presentation on a display. The digital representation includes a gesture-icon representing the action, the gesture-icon being overlaid on a digital twin of the physical object.

Abstract: A database performance tuning method is provided, including: receiving a performance tuning request of tuning a configuration parameter of a target database; obtaining a status indicator of the target database; and inputting the status indicator of the target database into a deep reinforcement learning model, and outputting a recommended configuration parameter of the target database. The deep reinforcement learning model includes a first deep reinforcement learning network and a second deep reinforcement learning network. The first deep reinforcement learning network is configured to provide a recommendation policy for outputting a recommended configuration parameter according to a status indicator, and the second deep reinforcement learning network is configured to evaluate the recommendation policy provided by the first deep reinforcement learning network.

Abstract: One variation of a method for serving interactive content to a user includes, at a visual element inserted into a document accessed by a computing device: loading a first frame from a digital video; in response to a scroll-down event that moves the visual element upward from a bottom of a window rendered on the computing device toward a top of the window, seeking from the first frame through a subset of frames in the digital video in a first direction at a rate corresponding to a scroll rate of the scroll-down event, the subset of frames spanning a duration of the digital video corresponding to a length of the scroll-down event; and, in response to termination of the scroll-down event with the visual element remaining in view within the window, playing the digital video forward from a last frame in the subset of frames in the digital video.

Abstract: A method for performing an entangling operation between trapped ions in a quantum computer includes selecting an amount of infidelity that is allowed in an entangling operation between two trapped ions in a quantum computer, computing a pulse function of a pulse to be applied to each of the two trapped ions based on gate operation conditions and the selected amount of infidelity, generating the pulse based on the computed pulse function, and applying the generated pulse to each of the two trapped ions to perform the entangling operation between the two trapped ions.

Abstract: A technical system controller is trained using a machine learning method. For this purpose, a chronological sequence of training data is detected for the machine learning method. The training data includes state data, which specifies states of the technical system, and control action data, which specifies control actions of the technical system. A chronological sequence of control action data is extracted specifically from the training data and is checked for a change over time. If a change over time is ascertained, a time window including the change is ascertained, and training data which can be found within the time window is extracted in a manner which is specific to the time window. The controller is then trained by the machine learning method using the extracted training data and is thus configured for controlling the technical system.

Abstract: A system for hardware installation is disclosed that includes a rack template system operating on a first processor and configured to receive location data and to provide a workflow of a series of rack image data sets. An agent system operating on a second processor and configured to display the series of rack image data sets and to prompt a user to enter user-generated image data sets. A rack validator operating on the first processor and configured to receive the user-generated image data sets and to determine whether the user-entered image data sets match the series of rack image data sets.

Abstract: Systems and methods are disclosed for improving on-chip security, while minimizes the latency and cost of security techniques to improve system-level performance and power simultaneously. The framework uses machine learning algorithms, such as an artificial neural network (ANN), for runtime attack detection with higher accuracy. Further, a learning-based attack mitigation method using deep reinforcement learning is disclosed, where the method may be used to isolate the malicious components and to optimize network latency and energy-efficiency.

Abstract: Techniques are provided for acceptance status classification of product-related data structures using models with multiple training periods. One method comprises obtaining data for a given product-related data structure; evaluating first features related to the given product-related data structure using the obtained data; applying the first features related to the given product-related data structure to one or more models trained using multiple different training periods to obtain a plurality of second features, wherein each of the second features indicates a prediction related to an acceptance status of the given product-related data structure by at least one model for a respective training period; and aggregating at least the second features to obtain a classification related to an aggregate acceptance status of the given product-related data structure. A weighting of at least some of the first and second features can be learned during a training phase.

Abstract: A system comprises an overhead bin including a door configured to open and close an opening of the overhead bin for access to and securing of an interior space of the overhead bin. A latch mechanism operatively connects the opening of the overhead bin to the door of the overhead bin to secure the door to the opening in a closed position, and to release the door from the opening for access to the interior space. A touchless input sensor can be operatively connected to the latch mechanism and a controller can be operatively connected to the latch mechanism and the touchless input sensor.

Abstract: Architectures or techniques are presented that can learn relationships between graphical elements presented by a user interface and physical conditions that exist in an environment. Furthermore, the architectures or techniques can, potentially based on the learned information, present the graphical elements to the user interface in a manner that is determined to be more efficient. For example, graphical elements that were historically accessed when a particular physical condition is true can be identified. These identified graphical elements can then be presented in a location of the user interface that is determined to be favorable to rapid or efficient selection at times with the particular physical condition is determined to be satisfied.

Abstract: One variation of a method for serving interactive advertisement content includes, at a visual element rendered within a window of a computing device: loading an interactive advertisement, including a digital advertisement and a mask overlaid the digital advertisement, into the visual element, the mask including a base layer and an aperture defining a second opacity less than a first opacity of the base layer; in response to a scroll event that moves the visual element a first position within the window, rendering the interactive advertisement within the visual element; and, in response to a scroll event that moves the visual element to a second position within the window, transforming the mask according to a sequence of transformations at a rate proportional to a scroll rate of the scroll event, the sequence of transformations corresponding to a sequence of vertical positions of the visual element within the window.

Abstract: A computer-implemented method is provided for allowing a custodian to manage a plurality of user accounts on a computing device via a device application. The plurality of user accounts includes a custodian user account and a shadowed user account. The computer-implemented method includes displaying a custodian user account on a graphical user interface of a computing device responsive to the device application being accessed on the computing device, managing the custodian user account in a first account context, and simultaneously: a) changing from the custodian user account to the shadowed user account via the device application, and b) changing the operating mode in the device application from the first account context to a second account context such that the shadowed user account is shadowed on the computing device by the custodian at less than full account control.

Abstract: Conversation user interfaces that are configured for virtual assistant interaction may include contextual interface items that are based on contextual information. The contextual information may relate to a current or previous conversation between a user and a virtual assistant and/or may relate to other types of information, such as a location of a user, an orientation of a device, missing information, and so on. The conversation user interfaces may additionally, or alternatively, control an input mode based on contextual information, such as an inferred input mode of a user or a location of a user. Further, the conversation user interfaces may tag conversation items by saving the conversation items to a tray and/or associating the conversation items with indicators.

Abstract: Systems and methods for activity-based device recommendations are disclosed. For example, historical usage data associated with a device may indicate that the device is likely to be associated with a given state at a given time. When the device is not in the anticipated state, a recommendation to transition the device state, for example, may be sent. Additionally, a determination of the activity state associated with the device, such as an active state, an asleep state, and/or an away state may be utilized to determine the recommendation to surface, to determine whether to send a recommendation, and when and/or how to send the recommendation.

Abstract: A client device installed with a client application having a graphical user interface (GUI) may be configured to (i) at a given time during a runtime session of the client application, identify a set of GUI elements within the GUI of the client application that is to be represented in a generic visualization of the GUI, (ii) generate a dataset that encodes the generic visualization of the GUI, wherein the generated dataset comprises a respective data structure for each GUI element in the identified set that encodes information for rendering a generic representation of the GUI element, and (iii) after generating the dataset that encodes the generic visualization of the GUI, transmit the generated dataset that encodes the generic visualization of the GUI to a back-end platform associated with a provider of the client application.

Abstract: A method for displaying a user interface used to manage a storage device is provided. The method is performed by a management device managing the storage device, and the method includes: obtaining, by using configuration content displayed in a first user interface, configuration data of a storage device configured for a first user; and after the first user logs in to the management device, displaying a second user interface corresponding to the first user, where the second user interface displays display content determined based on the configuration data.

Abstract: The present invention comprises a novel method for generating AI training data sets and evaluating the efficacy of AI algorithms against real data. The invention consists of both hardware and software devices. The described hardware devices are capable of providing known test object metadata and state information such that the appropriate attributes of a test object may be known a priori for use in AI algorithms. The described software devices are capable of performing the temporal association of the sensor and test object metadata and either building the training data set or statistically evaluating the accuracy of a pre-existing AI algorithm.

Abstract: In implementations of systems for estimating terminal event likelihood, a computing device implements a termination system to receive observed data describing values of a treatment metric and indications of a terminal event. Values of the treatment metric are grouped into groups using a mixture model that represents the treatment metric as a mixture of distributions. Parameters of a distribution are estimated for each of the groups and mixing proportions are also estimated for each of the groups. In response to receiving a user input requesting an estimate of a likelihood of the terminal event for a particular value of the treatment metric, the termination system generates an indication of the estimate of the likelihood of the terminal event for the particular value based on a distribution density at the particular value for each of the groups and a probability of including the particular value in each of the groups.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for collaboratively training an interaction prediction machine learning model using a plurality of user devices in a manner that respects user privacy. In one aspect, the machine learning model is configured to process an input comprising: (i) a search query, and (ii) a data element, to generate an output which characterizes a likelihood that a given user would interact with the data element if the data element were presented to the given user on a webpage identified by a search result responsive to the search query.

Abstract: Methods, computer systems, computer-storage media, and graphical user interfaces are provided for facilitating message composition, according to embodiments of the present invention. In one embodiment, message data associated with a message being composed is obtained. The message data is analyzed to determine a message type indicating a type of message and a message context representation representing a context provided within the message being composed. Context representations representing expected contexts associated with the message type of the message are identified. Thereafter, an absent context missing in the message being composed is determined based on a comparison of the message context representation with the set of context representations. A recommendation related to the absent context can be provided, for example, for display via a user interface.