Abstract: The disclosed embodiments include computer-implemented processes that generate adaptive textual explanations of output using trained artificial intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a first temporal interval, and based on an application of a trained artificial intelligence process to the input dataset, generate output data representative of a predicted likelihood of an occurrence of an event during a second temporal interval. Further, and based on an application of a trained explainability process to the input dataset, the apparatus may generate an element of textual content that characterizes an outcome associated with the predicted likelihood of the occurrence of the event, where the element of textual content is associated with a feature value of the input dataset. The apparatus may also transmit a portion of the output data and the element of textual content to a computing system.

Abstract: The disclosed embodiments include computer-implemented systems and processes that train adaptively and deployment of coupled machine-learning and explainability processes within distributed computing environments. By way of example, an apparatus may receive first interaction data associated with a first temporal interval from a computing system. Based on an application of a first and a second trained artificial-intelligence process to an input dataset that includes at least a subset of the first interaction data, the apparatus may generate output data indicative of a predicted likelihood of an occurrence of a target event during a second temporal interval, and may generate explainability data that characterizes the predicted likelihood. The apparatus may also transmit portions the output and explainability data to the computing system, and the computing system may modify an operation of an executed application program in accordance with at least one the output or explainability data.

Abstract: The disclosed embodiments include computer-implemented processes that generate adaptive textual explanations of output using trained artificial intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a first temporal interval, and based on an application of a trained artificial intelligence process to the input dataset, generate output data representative of a predicted likelihood of an occurrence of an event during a second temporal interval. Further, and based on an application of a trained explainability process to the input dataset, the apparatus may generate an element of textual content that characterizes an outcome associated with the predicted likelihood of the occurrence of the event, where the element of textual content is associated with a feature value of the input dataset. The apparatus may also transmit a portion of the output data and the element of textual content to a computing system.

Abstract: The disclosed embodiments include computer-implemented processes that flexibly and dynamically analyze a machine learning process, and that generate analytical output characterizing an operation of the machine learning process across multiple analytical periods. For example, an apparatus may receive an identifier of a dataset associated with the machine learning process and feature data that specifies an input feature of the machine learning process. The apparatus may access at least a portion of the dataset based on the received identifier, and obtain, from the accessed portion of the dataset, a feature vector associated with the machine learning process.

Abstract: The disclosed embodiments include computer-implemented processes that flexibly and dynamically analyze a machine learning process, and that generate analytical output characterizing an operation of the machine learning process across multiple analytical periods. For example, an apparatus may receive an identifier of a dataset associated with the machine learning process and feature data that specifies an input feature of the machine learning process. The apparatus may access at least a portion of the dataset based on the received identifier, and obtain, from the accessed portion of the dataset, a feature vector associated with the machine learning process.

Abstract: A modeling system trains a recurrent machine-learned model by determining a latent distribution and a prior distribution for a latent state. The parameters of the model are trained based on a divergence loss that penalizes significant deviations between the latent distribution the prior distribution. The latent distribution for a current observation is a distribution for the latent state given a value of the current observation and the latent state for the previous observation. The prior distribution for a current observation is a distribution for the latent state given the latent state for the previous observation independent of the value of the current observation, and represents a belief about the latent state before input evidence is taken into account.

Abstract: The disclosed embodiments include computer-implemented processes that flexibly and dynamically analyze a machine learning process, and that generate analytical output characterizing an operation of the machine learning process across multiple analytical periods. For example, an apparatus may receive an identifier of a dataset associated with the machine learning process and feature data that specifies an input feature of the machine learning process. The apparatus may access at least a portion of the dataset based on the received identifier, and obtain, from the accessed portion of the dataset, a feature vector associated with the machine learning process.

Abstract: A modeling system trains a recurrent machine-learned model by determining a latent distribution and a prior distribution for a latent state. The parameters of the model are trained based on a divergence loss that penalizes significant deviations between the latent distribution the prior distribution. The latent distribution for a current observation is a distribution for the latent state given a value of the current observation and the latent state for the previous observation. The prior distribution for a current observation is a distribution for the latent state given the latent state for the previous observation independent of the value of the current observation, and represents a belief about the latent state before input evidence is taken into account.

Abstract: To provide explanations for black box computer models, data samples are processed by the model to determine related feature attributions for each data sample, describing the extent to which feature values affect the model predictions for that data sample. A group of data samples is selected to be explained and the group is clustered into subgroups based on the feature attributions of the data samples. Because explanations related to feature attributions can be difficult to interpret or relate to input features, each of the subgroups is then described in the feature space, enabling ready interpretation of the groups at a semi-local level.

Abstract: A model evaluation system evaluates the effect of a feature value at a particular time in a time-series data record on predictions made by a time-series model. The time-series model may make predictions with black-box parameters that can impede explainability of the relationship between predictions for a data record and the values of the data record. To determine the relative importance of a feature occurring at a time and evaluated at an evaluation time, the model predictions are determined on the unmasked data record at the evaluation time and on the data record with feature values masked within a window between the time and the evaluation time, permitting comparison of the evaluation with the features and without the features. In addition, the contribution at the initial time in the window may be determined by comparing the score with another score determined by masking the values except for the initial time.

Abstract: The disclosed embodiments include computer-implemented processes that generate adaptive textual explanations of output using trained artificial intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a first temporal interval, and based on an application of a trained artificial intelligence process to the input dataset, generate output data representative of a predicted likelihood of an occurrence of an event during a second temporal interval. Further, and based on an application of a trained explainability process to the input dataset, the apparatus may generate an element of textual content that characterizes an outcome associated with the predicted likelihood of the occurrence of the event, where the element of textual content is associated with a feature value of the input dataset. The apparatus may also transmit a portion of the output data and the element of textual content to a computing system.

Abstract: A model visualization system analyzes model behavior to identify clusters of data instances with similar behavior. For a selected feature, data instances are modified to set the selected feature to different values evaluated by a model to determine corresponding model outputs. The feature values and outputs may be visualized in an instance-feature variation plot. The instance-feature variation plots for the different data instances may be clustered to identify latent differences in behavior of the model with respect to different data instances when varying the selected feature. The number of clusters for the clustering may be automatically determined, and the clusters may be further explored by identifying another feature which may explain the different behavior of the model for the clusters, or by identifying outlier data instances in the clusters.

Abstract: The disclosed embodiments include computer-implemented systems and processes that predict occurrences of targeted attrition events using trained artificial-intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a targeted participant during a first temporal interval. Based on an application of a trained artificial-intelligence process to the input dataset, the apparatus may generate output data representative of a predicted likelihood of an occurrence of an attrition event involving the targeted participant during a second temporal interval that is disposed subsequent to the first temporal interval, and that is separated from the first temporal interval by a buffer interval.

Abstract: A method is provided for driving an active matrix display device comprising a matrix of pixels configured to display an n-bit image data in an image frame by dividing the image frame for each pixel into n subframes; defining the n-bit image data to have n1 number of greater significant bits and n2 number of lesser significant bits, where n1+n2=n; and selecting the rows of pixels non-sequentially in the subframes corresponding to the n2 number of lesser significant bits such that there is no more than one row of pixel being selected in each subframe. The provided method can utilize the scan sequence in a more flexible way to make better use of the available scan time such that a higher display resolution or dynamic range can be achieved without increasing the scanning frequency.

Abstract: The disclosed embodiments include computer-implemented processes that flexibly and dynamically analyze a machine learning process, and that generate analytical output characterizing an operation of the machine learning process across multiple analytical periods. For example, an apparatus may receive an identifier of a dataset associated with the machine learning process and feature data that specifies an input feature of the machine learning process. The apparatus may access at least a portion of the dataset based on the received identifier, and obtain, from the accessed portion of the dataset, a feature vector associated with the machine learning process.

Abstract: A modeling system trains a recurrent machine-learned model by determining a latent distribution and a prior distribution for a latent state. The parameters of the model are trained based on a divergence loss that penalizes significant deviations between the latent distribution the prior distribution. The latent distribution for a current observation is a distribution for the latent state given a value of the current observation and the latent state for the previous observation. The prior distribution for a current observation is a distribution for the latent state given the latent state for the previous observation independent of the value of the current observation, and represents a belief about the latent state before input evidence is taken into account.

Abstract: According to embodiments of the invention, systems and methods are directed to an intelligent, real-time security protocol for encrypting certain communications which may be deemed to contain sensitive information. The disclosed technology may be carried out automatically or semi-autonomously. Systems and methods generally involve detecting which, if any, contents of a transmitted message contain sensitive information, which, if sent, may pose a security threat to the sender or another user. The disclosed technology may be carried out using a network node, server, computing device and/or any other apparatus or service for storing and transmitting information. The method may be carried out by a processor and computer readable storage medium. Software adapted to be used on a given computing device or via the web may be the platform from which the encryption is carried out.

Abstract: A container for washing, sterilization, transportation and sterile storage of articles for sterilization is provided. The container includes a sleeve and a frame adapted to receive articles for sterilization. The container includes at least one filtered opening to permit communication between the sterilization apparatus and the sterilization chamber for the communication of steam and air. In a first configuration, a front and rear wall of the frame engage the sleeve to create a sterilization chamber. The container may be stacked and stored in any orientation. In a second configuration, the frame rests or nests on top of the sleeve to permit access to and use of the sterilized articles. The container, may include one or a plurality of openings for communication between a sterilization apparatus and the sterilization chamber and one or more filters adjacent to the pluralities of openings.

Abstract: Integrated fuzzing techniques are described. A fuzzing system may employ a container configured as a separate component that can host different target pages to implement fuzzing for an application. A hosted target file is loaded as a subcomponent of the container and parsed to recognize functionality of the application invoked by the file. In at least some embodiments, this involves building a document object model (DOM) for a browser page and determining DOM interfaces of a browser to call based on the page DOM. The container then operates to systematically invoke the recognized functionality to cause and detect failures. Additionally, the container may operate to perform iterative fuzzing with multiple test files in an automation mode. Log files may be created to describe the testing and enable both self-contained replaying of failures and coverage analysis for multiple test runs.

Abstract: A container for washing, sterilization, transportation and sterile storage of articles for sterilization is provided. The container includes a sleeve and a frame adapted to receive articles for sterilization. The container includes at least one filtered opening to permit communication between the sterilization apparatus and the sterilization chamber for the communication of steam and air. In a first configuration, a front and rear wall of the frame engage the sleeve to create a sterilization chamber. The container may be stacked and stored in any orientation. In a second configuration, the frame rests or nests on top of the sleeve to permit access to and use of the sterilized articles. The container, may include one or a plurality of openings for communication between a sterilization apparatus and the sterilization chamber and one or more filters adjacent to the pluralities of openings.