Abstract: Enhanced methods for improving the performance of classifiers are described. A ground-truth labeled dataset is accessed. A classifier predicts a predicted label for datapoints of the dataset. A confusion matrix for the dataset and classifier is generated. A credibility interval is determined for a performance metric for each label. A first labels with a sufficiently large credibility interval is identified. A second label is identified, where the classifier is likely to confuse, in its predictions, the first label with the second label. The identification of the second label is based on instances of incorrect label predictions of the classifier for the first and/or the second labels. The classifier is updated based on a new third label that includes an aggregation of the first label and the second label. The updated classifier model predicts the third label for any datapoint that the classifier previously predicted the first or second labels.

Abstract: In various embodiments of the present disclosure, output data generated by a deployed machine learning model may be received. An input data anomaly may be detected based at least in part on analyzing input data of the deployed machine learning model. An output data anomaly may further be detected based at least in part on analyzing the output data of the deployed machine learning model. A determination may be made that the input data anomaly contributed to the output data anomaly based at least in part on comparing the input data anomaly to the output data anomaly. A report may be generated that is indicative of the input data anomaly and the output data anomaly, and the report may be transmitted to a client device.

Abstract: The present disclosure relates to utilizing a graph convolutional neural network to generate similarity probabilities between pairs of digital identities associated with digital transactions based on time dependencies for use in identifying fraudulent transactions. For example, the disclosed systems can generate a transaction graph that includes nodes corresponding to digital identities. The disclosed systems can utilize a time-dependent graph convolutional neural network to generate node embeddings for the nodes based on the edge connections of the transaction graph. Further, the disclosed systems can utilize the node embeddings to determine whether a digital identity is associated with a fraudulent transaction.

Abstract: In some embodiments, a computing system identifies a current engagement stage of a user with an online platform by applying a stage prediction model based on interaction data associated with the user. The interaction data describe actions performed by the user with respect to the online platform and context data associated with each of the actions. The computing system further identifies one or more critical events for promoting the user to transition from one engagement stage to a higher engagement stage based on the interaction data associated with the user. The computing system can make the identified current engagement stage of the user or the identified critical event to be accessible by the online platform so that user interfaces presented on the online platform can be modified to improve a likelihood of the user to transit from the current stage to a higher engagement stage.

Abstract: A device such as an autonomous mobile device may include an extensible mast or other structure that changes length during operation. A cable between electronics at the ends of the structure includes a data line for signals and a power line for electrical power. A deployed length of the cable is determined and used to determine the phase of an antinoise signal that is radiated using the power line. The antinoise signal destructively interferes with at least a portion of the radiated noise from the data line, reducing the overall amplitude of the radiated noise. The deployed length may also be used to adjust other parameters, such as equalizer settings for one or more of a transmitter or receiver that is connected to the data line.

Abstract: In some embodiments, a computing system identifies a current engagement stage of a user with an online platform by applying a stage prediction model based on interaction data associated with the user. The interaction data describe actions performed by the user with respect to the online platform and context data associated with each of the actions. The computing system further identifies one or more critical events for promoting the user to transition from one engagement stage to a higher engagement stage based on the interaction data associated with the user. The computing system can make the identified current engagement stage of the user or the identified critical event to be accessible by the online platform so that user interfaces presented on the online platform can be modified to improve a likelihood of the user to transit from the current stage to a higher engagement stage.

Abstract: Technologies for dynamic noise cancelation using noise patterns are described. One device includes a moveable assembly having first and second degrees of freedom. A component within the base assembly radiates electromagnetic energy in a radiation pattern as a noise source when operating and an antenna, coupled to a receiver, is disposed on the support member. The processing device, using noise profile data about the radiation pattern of the noise source, determines that the component is operating and a current angle between the component and the antenna. The processing device determines a difference value between the current angle and the first angle and causes the moveable assembly to move at least one of the antenna or the base assembly according to the difference value.

Abstract: Embodiments of the present disclosure are directed towards generating images conditioned on a desired attribute. In particular, an attribute-based image generation system can use a directional-GAN architecture to generate images conditioned on a desired attribute. A latent vector and a desired attribute are received. A feature subspace is determined for the latent vector using a latent-attribute linear classifier trained to determine a relationship between the latent vector and the desired attribute. An image is generated using the latent vector such that the image contains the desired attribute. In embodiments, where the feature space differs from a desired feature subspace, a directional vector is applied to the latent vector that shifts the latent vector from the feature subspace to the desired feature subspace. This modified latent vector is then used during generation of the image.

Abstract: A streaming media player includes a printed circuit board, a video processor, a wireless communications processor, and a patch antenna. The patch antenna includes dielectric material, a conductive patch, and a first antenna feed in a first position with respect to the conductive patch. The patch antenna includes a second antenna feed in a second position with respect to the conductive patch. The first position is orthogonal to the second position. In an embodiment, the second position is rotationally offset from the first position by 90 degrees around an axis through a center of the conductive patch. The streaming media player includes a connector coupled to the video processor and configured to removably couple to a connection port on a display device.

Abstract: A device includes a substrate and a video processor on the substrate. A first patch antenna is mounted to the substrate and configured to transmit and receive radio frequency signals in a frequency range. The first patch antenna is closer to a first end of the substrate than a second end of the substrate. A second patch antenna is mounted to the substrate and is configured to transmit and receive radio frequency signals in the frequency range. The second patch antenna is closer to the first end of the substrate than the second end of the substrate. The substrate includes a ground isolation region between at least one of the first patch antenna and the second patch antenna and the video processor. A media connector is on the substrate and electrically connected to the video processor.

Abstract: Embodiments of the present disclosure are directed towards generating images conditioned on a desired attribute. In particular, an attribute-based image generation system can use a directional-GAN architecture to generate images conditioned on a desired attribute. A latent vector and a desired attribute are received. A feature subspace is determined for the latent vector using a latent-attribute linear classifier trained to determine a relationship between the latent vector and the desired attribute. An image is generated using the latent vector such that the image contains the desired attribute. In embodiments, where the feature space differs from a desired feature subspace, a directional vector is applied to the latent vector that shifts the latent vector from the feature subspace to the desired feature subspace. This modified latent vector is then used during generation of the image.

Abstract: Forecasting a potential audience size and an unduplicated audience size for a digital campaign includes receiving an audience segment input and a time period input. The audience segment input is converted into multiple atomic target specifications. For each of the multiple atomic target specifications, a potential audience size is determined during the time period input by selecting a time series model based on a frequency of attribute values from the atomic target specification and combining the selected time series model with a frequent item set model. The potential audience size for each of atomic target specifications is aggregated over the time period input into a total potential audience size. The total potential audience size is output. The time series model and the frequent item set model are obtained using data from a historic bid request database.

Abstract: The present disclosure relates to utilizing a graph convolutional neural network to generate similarity probabilities between pairs of digital identities associated with digital transactions based on time dependencies for use in identifying fraudulent transactions. For example, the disclosed systems can generate a transaction graph that includes nodes corresponding to digital identities. The disclosed systems can utilize a time-dependent graph convolutional neural network to generate node embeddings for the nodes based on the edge connections of the transaction graph. Further, the disclosed systems can utilize the node embeddings to determine whether a digital identity is associated with a fraudulent transaction.

Abstract: In some embodiments, a computing system identifies a current engagement stage of a user with an online platform by applying a stage prediction model based on interaction data associated with the user. The interaction data describe actions performed by the user with respect to the online platform and context data associated with each of the actions. The computing system further identifies one or more critical events for promoting the user to transition from one engagement stage to a higher engagement stage based on the interaction data associated with the user. The computing system can make the identified current engagement stage of the user or the identified critical event to be accessible by the online platform so that user interfaces presented on the online platform can be modified to improve a likelihood of the user to transit from the current stage to a higher engagement stage.

Abstract: A user segmentation system is described that is configured to generate use segments and summarize user segments. In one example, the user segmentation system is configured to identify which attributes support a key performance indicator. This is used to generate rules that act as user segments of a user population. Further, the user segmentation system is configured to reduce overlap of user segments through summarization.

Abstract: Systems and methods are disclosed herein for distributing online ads with electronic content according to online ad request targeting parameters. One embodiment of this technique involves placing online test ads across multiple online ad request dimensions and tracking a performance metric for the online test ads. The performance of the online ad request dimensions is estimated based on the tracking of the performance metric for the online test ads and online ad request targeting parameters are established for spending a budget of a campaign to place online ads in response to online ad requests having particular online ad request dimensions. Online ads are then distributed based on using the online ad request targeting parameters to select online ad requests.

Abstract: Disclosed herein, among other things, are systems and methods for a hearing device antenna. One aspect of the present subject matter includes a hearing device configured to be worn in an ear of a wearer to perform wireless communication. The hearing device includes a housing, hearing electronics within the housing, and an inverted F antenna or loop antenna disposed at least partially in the housing and configured for performing 2.4 GHz wireless communication. In various embodiments, at least a portion of the antenna protrudes from an exterior of the housing.

Abstract: In some examples, a prototype model that includes a representative subset of data points (e.g., inputs and output classifications) of a machine learning model is analyzed to efficiently interpret the machine learning model's behavior. Performance metrics such as a critic fraction, local explanation scores, and global explanation scores are determined. A local explanation score capture an importance of a feature of a test point to the machine learning model determining a particular class for the test point and is computed by comparing a value of a feature of a test point to values for prototypes of the prototype model. Using a similar approach, global explanation scores may be computed for features by combining local explanation scores for data points. A critic fraction may be computed to quantify a misclassification rate of the prototype model, indicating the interpretability of the model.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for analyzing feature impact of a machine-learning model using prototypes across analytical spaces. For example, the disclosed system can identify features of data points used to generate outputs via a machine-learning model and then map the features to a feature space and the outputs to a label space. The disclosed system can then utilize an iterative process to determine prototypes from the data points based on distances between the data points in the feature space and the label space. Furthermore, the disclosed system can then use the prototypes to determine the impact of the features within the machine-learning model based on locally sensitive directions; region variability; or mean, range, and variance of features of the prototypes.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for accurately, efficiently, and flexibly generating digital graphical representations reflecting multiple data series in-scale utilizing dynamic y-axes. In particular, in one or more embodiments, the disclosed systems generate a normalized graphical representation portraying multiple data series in a common scale with a dynamic y-axis that portrays individualized data values based on user selection of various data series. Specifically, the presently disclosed systems and methods can generate normalized values for each of the included data series, plot the normalized values along a normalized y-axis, and include a dynamic y-axis that reflects the initial values of any of the included data series.