Abstract: Broadly speaking, embodiments of the present techniques provide techniques for delivering, when required, higher powers to SMA actuator wires by using a single controller/control circuit that implements pulse width modulation (PWM). Typically, when PWM is used to deliver power, the PWM frequency may be fixed, and power may be applied to each SMA actuator wire during each PWM cycle/period. The present techniques provide a method for delivering higher powers to SMA actuator wires (i.e. increasing the length of individual PWM pulses) without changing the duration of the PWM cycle/period. The present techniques also provide techniques for making accurate resistance measurements to determine position of a moveable component that is moved by the SMA actuator wires.

Abstract: The disclosure is directed to a query-driven machine learning platform for generating feature attributions and other data for interpreting the relationship between inputs and outputs of a machine learning model. The platform can receive query statements for selecting data, training a machine learning model, and generating model explanation data for the model. The platform can distribute processing for generating the model explanation data to scale in response to requests to process selected data, including multiple records with a variety of different feature values. The interface between a user device and the machine learning platform can streamline deployment of different model explainability approaches across a variety of different machine learning models.

Abstract: Broadly speaking, embodiments of the present techniques provide techniques for delivering, when required, higher powers to SMA actuator wires by using a single controller/control circuit that implements pulse width modulation (PWM). Typically, when PWM is used to deliver power, the PWM frequency may be fixed, and power may be applied to each SMA actuator wire during each PWM cycle/period. The present techniques provide a method for delivering higher powers to SMA actuator wires (i.e. increasing the length of individual PWM pulses) without changing the duration of the PWM cycle/period. The present techniques also provide techniques for making accurate resistance measurements to determine position of a moveable component that is moved by the SMA actuator wires.

Abstract: Broadly speaking, embodiments of the present techniques provide techniques for delivering, when required, higher powers to SMA actuator wires by using a single controller/control circuit that implements pulse width modulation (PWM). Typically, when PWM is used to deliver power, the PWM frequency may be fixed, and power may be applied to each SMA actuator wire during each PWM cycle/period. The present techniques provide a method for delivering higher powers to SMA actuator wires (i.e. increasing the length of individual PWM pulses) without changing the duration of the PWM cycle/period. The present techniques also provide techniques for making accurate resistance measurements to determine position of a moveable component that is moved by the SMA actuator wires.

Abstract: An inspection feature for an adhesive bond portion between parts of a component comprising the inspection feature extending from a surface of the part of the component a predetermined bond line thickness, the inspection feature having a density configured to imitate a defect of the adhesive bond portion responsive to a non-destructive inspection scan.

Abstract: Broadly speaking, embodiments of the present techniques provide techniques for delivering, when required, higher powers to SMA actuator wires by using a single controller/control circuit that implements pulse width modulation (PWM). Typically, when PWM is used to deliver power, the PWM frequency may be fixed, and power may be applied to each SMA actuator wire during each PWM cycle/period. The present techniques provide a method for delivering higher powers to SMA actuator wires (i.e. increasing the length of individual PWM pulses) without changing the duration of the PWM cycle/period. The present techniques also provide techniques for making accurate resistance measurements to determine position of a moveable component that is moved by the SMA actuator wires.

Abstract: An inspection feature for an adhesive bond portion between parts of a component comprising the inspection feature extending from a surface of the part of the component a predetermined bond line thickness, the inspection feature having a density configured to imitate a defect of the adhesive bond portion responsive to a non-destructive inspection scan.

Abstract: The computer-implemented systems, methods, and interfaces for collecting, organizing, and conveying information and preferences regarding certain end-of-life issues. The integrated systems, methods and interfaces guide the user to create a customized output that communicates certain information and preferences about estate planning, end-of-life issues, or final arrangements for the user, for user and their spouse, or for another third party. Inputs are solicited from the user and those inputs and other interactions are used in a decision engine to dynamically determine which queries should be presented to the user, what and how inputs are requested from the user, how the interfaces are rendered, and the ultimate content of the output. A customized output is automatically generated that organizes the user's inputs into a more productive form and combines the user's inputs with additional content and instructions.

Abstract: Methods and computer-storage media having computer-executable instructions embodied thereon that facilitate generating a machine-learned model for ranking search results using click-based data are provided. Data is referenced from user queries, which may include search results generated by general search engines and vertical search engines. A training set is generated from the search results and click-based judgments are associated with the search results in the training set. Based on click-based judgments, identifiable features are determined from the search results in a training set. Based on determining identifiable features in a training set, a rule set is generated for ranking subsequent search results.

Abstract: Methods, systems, and media are provided for identifying and clustering queries that are rising in popularity. Resultant clustered queries can be compared to other stored queries using textual and temporal correlations. Fresh indices containing information and results from recently crawled content sources are searched to obtain the most recent query activity. Historical indices are also searched to obtain temporally correlated information and results that match the clustered query stream. A weighted average acceleration of a spike can be calculated to distinguish between a legitimate spike and a non-legitimate spike. Legitimate clusters are combined with other stored clusters and presented as grouped content results to a user output device.

Abstract: Methods and computer-storage media having computer-executable instructions embodied thereon that facilitate generating a machine-learned model for ranking search results using click-based data are provided. Data is referenced from user queries, which may include search results generated by general search engines and vertical search engines. A training set is generated from the search results and click-based judgments are associated with the search results in the training set. Based on click-based judgments, identifiable features are determined from the search results in a training set. Based on determining identifiable features in a training set, a rule set is generated for ranking subsequent search results.

Abstract: Methods, systems, and media are provided for identifying and clustering queries that are rising in popularity. Resultant clustered queries can be compared to other stored queries using textual and temporal correlations. Fresh indices containing information and results from recently crawled content sources are searched to obtain the most recent query activity. Historical indices are also searched to obtain temporally correlated information and results that match the clustered query stream. A weighted average acceleration of a spike can be calculated to distinguish between a legitimate spike and a non-legitimate spike. Legitimate clusters are combined with other stored clusters and presented as grouped content results to a user output device.