Abstract: A processor may receive local updates for a current global model from a plurality of client computing devices, each local update being determined by one of the plurality of client computing devices based on a local dataset on the client computing device. The processor may determine a domain-specific aggregate of the local updates from each subset of the plurality of client computing devices. The processor may determine an updated global model based on the domain-specific aggregate of the local updates for each subset of the plurality of client computing devices.

Abstract: Features are described for controlling the functionality of an electronic device, where the device operates according to a restricted mode of operation in which functions that the electronic device is otherwise capable of performing are not immediately available.

Abstract: Multiparty object recognition systems and methods are disclosed. A method of interactively manipulating virtual object data, wherein an object database is configured to store first party object data that corresponds to a first real-world object and is further configured to store second party object data that corresponds to a second real-world object, includes obtaining the first party object data and the second party object data for storage within the object database. Access to the object database is controlled such that the first party object data and the second party object data is accessible to the first party and the second party. Modification of the first party object data by the second party is facilitated to generate modified first party object data that is in accordance with at least one context parameter of the second party object data, and the modified first party object data is communicated to the first party.

Abstract: Methods and apparatus to enable a trading device to accept a user input are disclosed. An example method includes generating, via a computing device, a user interface of a trading application, wherein the user interface includes a locked portion that displays market data. The example method also includes detecting a gestural input with respect to the user interface. The example method also includes detecting a gestural event with respect to the user interface associated with the gestural input and, in response to the detected gestural event, unlocking the locked portion of the user interface.

Abstract: A machine learning model engine executes a machine learning model that has been trained with training data and processes scoring data to generate predictions. A machine learning model analyzer is configured to evaluate the machine learning model. The machine learning model analyzer determines a plurality of drift metrics for the plurality of input variables to compare the distribution of the training data to the distribution of the scoring data. Each of the plurality of drift metrics is associated with one of the plurality of input variables. The machine learning model analyzer also determines an overall drift metric for the combination of the input variables. The plurality of input variables are weighted in the overall drift metric in accordance with the plurality of feature importances. The machine learning model analyzer generates an alert based on the overall distribution of the training data relative to the overall distribution of the scoring data.

Abstract: Techniques for improving the convenience of activating different computing applications on a mobile computing device are disclosed. Sensors associated with a mobile computing device (e.g., accelerometers, gyroscopes, light sensors, microphones, image capture sensors) may receive inputs of various physical conditions to which the mobile computing device is being subjected. Based on one or more of these inputs, the mobile computing device may automatically select a content presentation mode that is likely to improve the consumption of the content by the user. In other embodiments, image analysis may be used to access different mobile computing applications.

Abstract: In one implementation, a method is performed for selecting a UI element with eye tracking-based attention accumulators. The method includes: while a first UI element is currently selected, detecting a gaze direction directed to a second UI element; in response to detecting the gaze direction directed to the second UI element, decreasing a first attention accumulator value associated with the first UI element and increasing a second attention accumulator value associated with the second UI element; in accordance with a determination that the second attention accumulator value exceeds the first attention accumulator value, deselecting the first UI element and selecting the second UI element; and in accordance with a determination that the second attention accumulator value does not exceed the first attention accumulator value, maintaining selection of the first UI element.

Abstract: The disclosed embodiments are directed to a media capture lock affordance for a graphical user interface displayed by a media capture device. The media capture lock affordance allows a user to lock and unlock a capture state of the media capture device using a simple and intuitive touch gesture that can be applied by the user's finger (e.g., the user's thumb) while holding the media capture device in one hand.

Abstract: In various embodiments, a workflow application generates and evaluates designs that reflect stylistic preferences. In operation, the workflow application determines a target style based on input received via a graphical user interface (GUI). Notably, the target style characterizes a first set of designs. The workflow application then generates stylized design(s) based on stylization algorithm(s) associated with the target style. Subsequently, the workflow application, displays a subset of the stylized design(s) via the GUI. A stylized design included in the subset of stylized design(s) is ultimately selected for production via the GUI. Advantageously, because the workflow application can substantially increase the number of designs that can be generated and evaluated based on the target style in a given amount of time, relative to more manual prior art techniques, the overall quality of the stylized design selected for production can be improved.

Abstract: Aspects of the present disclosure are directed to a mini-map coordination system that can facilitate interactions between co-located and non-co-located users by providing a min-map through an artificial reality system. The mini-map can be a representation of a virtual space that corresponds to a real-world space in which some users are located and that other users join virtually. Users can join the space by entering the real-world space or by remotely logging into the virtual space. Users who have joined the virtual space can be represented in the mini-map by avatars. Users moving their avatars around the mini-map can trigger interactions, such as automatically initiating a holographic call between the users whose avatars come within a threshold distance of each other. The system can allow remote users to observe social norms such as requiring a user to “knock” before their avatar is allowed to enter a private space.

Abstract: The present disclosure generally relates to methods and user interfaces for managing visual content at a computer system. In some embodiments, methods and user interfaces for managing visual content in media are described. In some embodiments, methods and user interfaces for managing visual indicators for visual content in media are described. In some embodiments, methods and user interfaces for inserting visual content in media are described. In some embodiments, methods and user interfaces for identifying visual content in media are described. In some embodiments, methods and user interfaces for translating visual content in media are described.

Abstract: Methods and systems disclosed herein relate generally to systems and methods for using a machine-learning model to predict user-engagement levels of users in response to presentation of future interactive content. A content provider system accesses a machine-learning model, which was trained using a training dataset including previous user-device actions performed by a plurality of users in response to previous interactive content. The content provider system receives user-activity data of a particular user and applies the machine-learning model to the user-activity data, in which the user-activity data includes user-device actions performed by the particular user in response to interactive content. The machine-learning model generates an output including a categorical value that represents a predicted user-engagement level of the particular user in response to a presentation of the future interactive content.

Abstract: Systems and methods are disclosed for generating an acoustic authentication data entry interface. One method comprises generating a random sequence of characters and a visual user interface element comprising a plurality sections, each section of the visual user interface element being associated with a respective character of the generated random sequence of characters. A section of the visual user interface elements is displayed to a user. Concurrently, an audio recording of a character associated with the displayed section is played to the user. Based on determining user selection of the displayed section, the character associated with the displayed section is logged as part of an authentication data. When all of the characters constituting the authentication data are logged, an electronic transaction authorization request is sent to an acquirer processor.

Abstract: The relationship between the smell or taste of an object and the expression of the smell or taste can be grasped, and the user can grasp what smell or taste they prefer. In the single-sample display mode, a system displays a group of expressions relating to the olfactory sense stimulated by a sample, and if any expression is selected by the user, the system displays a relationship image indicating the relationship between the selected expression and other samples corresponding to the olfactory sense associated with the expression. In addition, in the multiple-sample display mode, the system displays, for each of plural samples, a group of expressions relating to the sense of smell stimulated by each sample, and displays an expression common to plural samples among the group of expressions.

Abstract: The system receives an indication of an issue associated with a wireless telecommunication network and an indication of an operator capable of resolving the issue. The system sends a notification to an AR/VR device associated with the operator. The notification indicates the issue and prompts the operator to join a virtual collaboration room. The system receives a request to join the virtual collaboration room from the operator based on a gesture or a voice command detected by the AR/VR device. The system creates the virtual collaboration room, via a 5G wireless telecommunication network, including a screen shared among multiple operators. The system records operations performed in the virtual collaboration room until a resolution to the issue has been determined.

Abstract: Methods and apparatus to enable a trading device to accept a user input are disclosed. An example method includes generating, via a computing device, a user interface of a trading application, wherein the user interface includes a locked portion that displays market data. The example method also includes detecting a gestural input with respect to the user interface. The example method also includes detecting a gestural event with respect to the user interface associated with the gestural input and, in response to the detected gestural event, unlocking the locked portion of the user interface.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media relate to a method for providing video communications with dynamic virtual backgrounds within a communication platform. The system provides a user interface for the configuration of a virtual background configuration template. The user interface receives the placement of at least one virtual background boundary areas that may be associated with at least one particular virtual backgrounds to be used for video communications. The selection of the configuration template to be used and/or the specific virtual backgrounds to be used for a video meeting may be determined based on rules as applied to contextual information of a planned meeting defined in a calendaring system.

Abstract: Methods and devices for a feedback loop system, associated with delivery of content related to a software application, are disclosed. A method includes determining, for the content, a difference between a target output and a performance output. The performance output is an aggregate of respective unit outputs for unit(s) of the content. The method includes determining an input value required to re-perform at least one of the units. The re-performance can modify the difference. The input value, based on a probabilistic calculation of possible outcomes of the re-performance, is normalized based on a pre-determined baseline input value. The method includes determining, based on the normalized input value, an adjusted unit output associated with the re-performance. The method includes generating, based on the respective unit outputs and the adjusted unit output, and providing for display on a GUI, a graphical display layout comprising a visual representation of the unit(s).

Abstract: Some embodiments include an ambiguated application that can perform first functions, e.g., a communication application functions, when the ambiguated application is in a first state, and perform second functions, e.g., game functions, when the ambiguated application is in a second state. The ambiguated application in the first state and the ambiguated application in the second state share a same graphic user interface (GUI). When a functional object of the GUI is selected, the ambiguated application performs a first function if the ambiguated application is in a first state. In addition, when the same functional object of the GUI is selected, the ambiguated application performs a second function if the ambiguated application is in a second state.

Abstract: Methods, systems and computer readable media are provided for configuring machine learning systems to automatically and dynamically select a machine learning model based on statistical profiling of received data to improve machine learning applications for high variance data. Data is received from a system in operation. A profile is computed for the received data. A database comprising a plurality of stored profiles for a dataset is accessed, wherein each stored profile corresponds to a distinct pattern identified in the dataset. The computed profile is compared to each of the stored profiles to determine whether the computed profile matches one or more of the stored profiles. When one or more stored profiles match the computed profile, a matching profile is selected by the machine learning system. The received data is processed using a ML model associated with the matching profile.