Abstract: A system and method for creating a machine learning (ML) classifier for a database uses a weakly-supervised training data set created automatically from database items on the basis of a human-created keyword set. The automatically created training data set is used to construct one or more deep learning classifier checkpoints, which can then be compared with one another and with a classifier based on the original keyword set in order to select a classifier for use by other users viewing the database.

Abstract: Systems and methods for network optimization using end user telemetry are disclosed. In one embodiment, a method for optimizing incoming communication routing may include: (1) establishing, by a data center computer program executed by a data center computer processor, a data connection with an end user electronic device, the data connection using a first data communication route; (2) collecting, by the data center computer program, a metric for the data connection; (3) determining, by the data center computer program, that the metric is outside of an acceptable range; (4) determining, by the data center computer program, that a cause for the metric being outside of the acceptable range is external to the data center; and (5) re-routing, by the data center computer program, the data connection to a second data communication route.

Abstract: A system and method for creating a machine learning (ML) classifier for a database uses a weakly-supervised training data set created automatically from database items on the basis of a human-created keyword set. The automatically created training data set is used to construct one or more deep learning classifier checkpoints, which can then be compared with one another and with a classifier based on the original keyword set in order to select a classifier for use by other users viewing the database.

Abstract: Described herein are systems and methods for predicting a metric value for an entity associated with a query node in a graph that represents a network. In embodiments, using a user's profile as the query node, a metric about that user may be estimated based, at least in part, as a function of how well connected the query node is to a whitelist of “good” users/nodes in the network, a blacklist of “bad” users/nodes in the network, or both. In embodiments, one or more nodes or edges may be weighted when determining a final score for the query node. In embodiments, the final score regarding the metric may be used to take one or more actions relative to the query node, including accepting it into a network, allowing or rejecting a transaction, assigning a classification to the node, using the final score to compute another estimate for a node, etc.

Abstract: Technology is disclosed herein for enhanced similarity search. In an implementation, a search environment includes one or more computing hardware, software, and/or firmware components in support of enhanced similarity search. The one or more components identify a modality for a similarity search with respect to a query object. The components generate an embedding for the query object based on the modality and based on connections between the query object and neighboring nodes in a graph. The embedding for the query object provides the basis for the search for similar objects.

Abstract: Systems, devices, and methods are disclosed for characterizing joint attention. A method includes dynamically obtaining video streams of participants; dynamically obtaining gaze streams; dynamically providing a cue to the participants to view the object; dynamically detecting a joint gaze based on the gaze streams focusing on the object over a time interval; and dynamically providing feedback based on detecting the joint gaze.

Abstract: Embodiments provide methods and systems for predicting chargeback behavioral data of an account holder. The method performed by a server system includes accessing payment transaction data associated with the account holder from a transaction database. The payment transaction data includes a set of transaction indicators corresponding to payment transactions performed by the account holder within a predetermined time period. The method further includes generating a set of transaction features based on the set of transaction indicators. Furthermore, the method includes computing, via a chargeback risk prediction model, a set of chargeback risk probability scores corresponding to one or more time intervals associated with the account holder based, at least in part, on the set of transaction features. The method also includes transmitting a notification to an issuer server associated with the account holder based, at least in part, on the set of chargeback risk probability scores.

Abstract: Implementations augment images with depth information to support hologram display. An edge system can receive, from a source system, images of a user. For example, the images can be two-dimensional images captured by multiple cameras at different perspectives (e.g., stereoscopic images), or single perspective images. The edge system can estimate depth information using the images, for example by processing the images using an engine and one or more machine learning models, and generate depth encoded images. The edge system can then transmit the depth encoded images to a target system, which can ultimately display a hologram of the user using the depth encoded images. Accordingly, implementations can offload, from end-user devices (e.g., the source system and/or target system), hologram workloads to an edge system loaded with an engine and machine learning model(s).

Abstract: A method for controlling a steering system of a vehicle during an autonomous steering development mode may include performing, by one or more computing devices, high-authority autonomous steering control of a steering system of the vehicle. The method may further include receiving, by the one or more computing devices, an input from at least one sensor of the steering system indicative of manual operation of the steering system by an operator of the vehicle. Additionally, the method may include transitioning, by the one or more computing devices, from the high-authority autonomous steering control to a low-authority autonomous steering control of the steering system for a predetermined time period in response to receiving the input from the at least one sensor.

Abstract: A framework for implementing just-in-time decision support analytics within a business application deployment are provided. In one set of embodiments, the framework enables an application user to be presented with analytics that are in-context and in-place with respect to an operational workflow carried out by the user, where “in-context” means that the presented analytics are directly relevant to, and tailored for, the specific business context of the user's operational workflow, and “in-place” means that the analytics are displayed to the user within the same UI/application used to execute the operational workflow, and at the same time the workflow is actually executed. These characteristics advantageously ensure that the user is provided with the insights he/she needs to make confident business decisions and facilitates real-time decision making for time-critical operations.

Abstract: A method for discovering and diagnosing network anomalies. The method includes receiving key performance indicator (KPI) data and alarm data. The method includes extracting features based on samples obtained by discretizing the KPI data and the alarm data. The method includes generating a set of rules based on the features. The method includes identifying a sample as a normal sample or an anomaly sample. In response to identifying the sample as the anomaly sample, the method includes identifying a first rule that corresponds to the sample, wherein the first rule indicates symptoms and root causes of an anomaly included in the sample. The method further includes applying the root causes to derive a root cause explanation of the anomaly and performing a corrective action to resolve the anomaly based on the first rule.

Abstract: Methods and systems are described for verifying an identity of a user through contextual knowledge-based authentication. The system described uses contextual knowledge-based authentication. By verifying an identity of a user through contextual knowledge-based authentication, the verification is both more secure and more intuitive to the user. For example, by relying on confidential and/or proprietary information, the system may generate verification questions, the answers to which are known only by the user.

Abstract: A method of controlling power in a transmission system may include determining a first transmit power of a first transmit path, determining a second transmit power of a second transmit path, and controlling the first transmit path and the second transmit path based on a combination of the first transmit power and the second transmit power. The combination of the first transmit power and the second transmit power may include a sum of the first transmit power and the second transmit power. Controlling the first transmit path and the second transmit path may include determining a first effective power target for the first transmit path based on the first transmit power and the second transmit power, and determining a second effective power target for the second transmit path based on the first transmit power and the second transmit power.

Abstract: A wearable face covering may include a mask including a filter and a cap, wherein the cap is configured to prevent any gas passing through the filter in a first direction from exiting the mask in the first direction; and a face shield including a partially-transparent screen, wherein the face shield is pivotally coupled to the mask.

Abstract: Various embodiments described herein support or provide for annotation of a media asset, such as an audio asset or a video asset, based on one or more events identified within content of the media asset. In particular, some embodiments can determine one or more of the following details with respect to content of a given media asset, which can represent annotations that enable determination of contextual information for the given media asset: events; event classification labels for events; subclassifications labels for events; scenes comprising events; attributes of scenes; themes presented by the content; and title-level attributes of the given media asset.

Abstract: A liquid electrophotographic (LEP) printing device that includes a photo-imaging plate (PIP) to receive a liquid printing fluid, the liquid printing fluid including a pigment incorporated into a resin, a charge conductor, and a carrier liquid, and a transfer roller to transfer the liquid printing fluid from the PIP to a fabric substrate while wet.

Abstract: A method and apparatus for identifying blood vessels in ultrasound images and displaying blood vessels in ultrasound images are described. In some embodiments, the method is implemented by a computing device and includes assigning, with a neural network implemented at least partially in hardware of the computing device, one of a vein classification and an artery classification to one or more blood vessels in ultrasound images. The method also includes determining a misclassification for one blood vessel that denotes the neural network assigning the one of the vein classification and the artery classification to the one blood vessel in one ultrasound image and the other of the vein classification and the artery classification to the one blood vessel in additional ultrasound images. The method includes displaying, in the one ultrasound image, an indication of the other of the vein classification and the artery classification for the one blood vessel.

Abstract: A system for determining instructor effectiveness scores for interactive learning sessions delivered via an online learning platform to a plurality of learners is presented. The system includes a data module and a processor. The data module is operatively coupled to the online learning platform and a computing device used by an instructor to deliver the online learning sessions, the data module configured to access in-session data, post-session data, and content metadata for a first plurality of learning sessions delivered by the instructor. The processor is operatively coupled to the data module, and includes a feature generator, a score estimator, and a notification module.

Abstract: Existing systems for document processing are either based on a supervised approach using annotated tags, and these systems identify section-based data from the unstructured documents without considering the statistical variations in content, which results in highly inaccurate content extraction. The disclosure herein generally relates to document processing, and, more particularly, to method and system for document indexing and retrieval. The system provides a mechanism to correlate unique words in a document with different topics identified in the document, based on a word pattern identified from the document. The correlations are captured in a knowledge graph, and can be further used in applications such as but not limited to document retrieval.