Abstract: Many factors contribute to the final predictive accuracy of a trained machine learning model, but the model's predictive behavior depends unavoidably on each of the samples used to train it. After a model is trained, some of the training samples may be found later to be undesired. Undesired samples could represent personal information of a consumer who has asked to be “forgotten”, incorrectly measured or low-quality input data, irrelevant data used to train a base model later used in transfer learning, or samples found to be unwanted for any other reason. Heretofore, the only technique available to remove the effect of undesired samples was to retrain the model with those samples removed from the training set. This invention provides a method to remove the effect of undesired samples after the model is trained, without the need to retrain the entire model from scratch.

Abstract: The present disclosure relates to a method for a weighting graph comprising nodes representing entities and edges representing relationships between entities in accordance with one or more domains. The method comprises: pre-processing the graph comprising assigning weights to the nodes and/or the edges of the graph in accordance with a specific domain of the domains, wherein the weight indicates a domain specific data quality problem of attribute values representing an edge of the edges and/or an entity involved in that edge. The weighted graph may be provided for enabling a processing of the graph in accordance with the specific domain.

Abstract: The invention relates to supports (1) for receiving a surgical implant, in particular a bone plate (2), containing an implant receptacle (3), the implant receptacle (3) being of substantially elongate form along a longitudinal axis (4) and having a first part (5) and a second part (6), the first part (5) having a shaft (7) for receiving the surgical implant (2) at a recess (13) of the implant (2), the second part (6) having a first fastening portion (8) for fastening to a holding portion (9) of a container (114). The support (1) furthermore contains at least one elastic element (10), in particular a spring, for securing the implant, which is designed to secure an implant, which is held on the implant receptacle (3), by a force component substantially perpendicular to the longitudinal axis (4). Also disclosed are supports (100) for receiving at least one surgical item, in particular an implant, in particular a screw (101).

Abstract: In an approach, a processor receives an unstructured text document. A processor extracts at least one unrecognized token from the unstructured text document. A processor identifies at least one structured data element in a predefined set of data sources, where the at least one structured data element is related to the at least one extracted unrecognized token from the unstructured text document. A processor relates a label associated with the identified at least one structured data element to the unstructured text document.

Abstract: Methods, computer program products and/or systems are provided that perform the following operations: obtaining a first graph comprising first nodes representing first entities and first edges representing relationships between first entities, the first nodes being associated with first entity attributes descriptive of the first entities represented by the first nodes, the first edges being associated with first edge attributes descriptive of the relationships represented by the first edges; determining a first subgraph for a certain node of the first nodes of the first graph, the first subgraph including the certain node and at least one neighboring node of the certain node; and determining a data quality issue regarding the certain node based, at least in part, on applying one or more applicable rules of a set of data quality rules to first entity attribute values and first edge attribute values of the first subgraph.

Abstract: Embodiments of the present invention determines duplicates in a graph. The graph comprises nodes representing entities and edges representing relationships between the entities. The method comprises: identifying at least two nodes in the graph. A neighborhood subgraph may be determined for each of the two nodes. The neighborhood subgraph includes the respective node. The method further comprises determining whether the two nodes are duplicates with respect to each other, based on a result of a comparison between the two subgraphs.

Abstract: The present invention is directed to various polycyclic compounds and methods of using these compounds to treat a variety of diseases including metabolic diseases such as obesity, diabetes, nonalcoholic fatty liver disease; cardiovascular diseases such as hypertension and stroke; neurological diseases, male infertility, muscular disorders, and immune disorders.

Abstract: Techniques for predicting an impact of one or more events on service demand are disclosed. Some embodiments include first and second sets of data characterising properties of historic events using metadata tags, and demand for services that are then filtered to distinguish ordinary demand from extra-ordinary demand. Machine learning is used to determine correlations between metadata tags and extra-ordinary demand to produce a third data set operable for predictive determinations of future event on service demand.

Abstract: Methods, computer program products and/or systems are provided that perform the following operations: obtaining a first graph comprising first nodes representing first entities and first edges representing relationships between first entities, the first nodes being associated with first entity attributes descriptive of the first entities represented by the first nodes, the first edges being associated with first edge attributes descriptive of the relationships represented by the first edges; determining a first subgraph for a certain node of the first nodes of the first graph, the first subgraph including the certain node and at least one neighboring node of the certain node; and determining a data quality issue regarding the certain node based, at least in part, on applying one or more applicable rules of a set of data quality rules to first entity attribute values and first edge attribute values of the first subgraph.

Abstract: A method, system and computer program product for classifying a data collection of data of a predefined domain. A hierarchical representation scheme describing terms of the domain and one or more relationships between the terms is provided. At least one classifier may be applied on the data collection, resulting in a set of term assignments. Each term assignment of the term assignments associates a term candidate with a respective confidence value to the collection or to one or more data items of the collection. At least one of the term assignments may be refined based on the representation scheme and the set of term assignments.

Abstract: A computer device identifies a set of documents for classification. The computing device classifies documents of a first subset of the set of documents based, at least in part, on a text analysis of the documents of the first subset. The computing device trains a document classifier using, as training data: (i) results of the classifying of the documents of the first subset, and (ii) metadata associated with the documents of the first subset. The computing device classifies documents of a second subset of the set of documents by providing metadata of the documents of the second subset to the trained document classifier.

Abstract: The present disclosure relates to a method for a weighting graph comprising nodes representing entities and edges representing relationships between entities in accordance with one or more domains. The method comprises: pre-processing the graph comprising assigning weights to the nodes and/or the edges of the graph in accordance with a specific domain of the domains, wherein the weight indicates a domain specific data quality problem of attribute values representing an edge of the edges and/or an entity involved in that edge. The weighted graph may be provided for enabling a processing of the graph in accordance with the specific domain.

Abstract: Embodiments of the present invention determines duplicates in a graph. The graph comprises nodes representing entities and edges representing relationships between the entities. The method comprises: identifying at least two nodes in the graph. A neighborhood subgraph may be determined for each of the two nodes. The neighborhood subgraph includes the respective node. The method further comprises determining whether the two nodes are duplicates with respect to each other, based on a result of a comparison between the two subgraphs.

Abstract: Media content is provided, via an online service, for consumption by a user of a user device. The media content is provided for playback within a media player presented on a screen of the user device. In-stream content is provided to the user device for automatic playback within the media player without the playback of the media content. An indication of user interaction with the in-stream content that is automatically played back within the media player without the playback of the media content is received. Responsive to the user interaction with the in-stream content satisfying a user interest criterion, companion content is selected to be sent to the user device. The companion content is related to the in-stream shared content.

Abstract: A method, system and computer program product for classifying a data collection of data of a predefined domain. A hierarchical representation scheme describing terms of the domain and one or more relationships between the terms is provided. At least one classifier may be applied on the data collection, resulting in a set of term assignments. Each term assignment of the term assignments associates a term candidate with a respective confidence value to the collection or to one or more data items of the collection. At least one of the term assignments may be refined based on the representation scheme and the set of term assignments.

Abstract: A system including a monitoring unit to monitor in-stream shared content and content served via the online service to a user; an in-stream shared content receiving unit to receive information about the in-stream shared content served with the content; a companion shared content selection unit to select the companion shared content based on the monitored in-stream shared content and content, and the received information; and a transmitting unit to transmit the selected companion shared content to the online service.

Abstract: An access system for a vehicle may include a controller. The controller may be configured to respond to receiving an unlock signal indicative of an unlock request by causing a compartment closure to unlock for a predetermined time. Or the controller may be configured to respond to receiving an unlock signal indicative of an unlock request and a vehicle operation signal indicative of a vehicle secure state by causing a compartment closure to unlock for a predetermined time. Upon expiration of the predetermined time, the controller may cause the compartment closure to lock. The controller may be configured to respond to receiving an unlatch signal indicative of an unlatch request during the predetermined time by causing the compartment closure to unlatch.

Abstract: A device for monitoring signal levels of signals that are generated, for the purpose of detecting a magnetic field, by a plurality of Hall sensors includes a first, second, and third input and a diagnostic device. The first input is configured to receive a first signal from a first Hall sensor. A first electrical resistor is connected between the first input and a central point. The second input is configured to receive a second signal from a second Hall sensor. A second electrical resistor is connected between the second input and the central point. The third input is configured to receive a third signal from a third Hall sensor. A third electrical resistor is connected between the third input and the central point. The diagnostic device is connected to the central point and is configured to determine a position of the detected magnetic field using an average value.

Abstract: A system including a monitoring unit to monitor in-stream shared content and content served via the online service to a user; an in-stream shared content receiving unit to receive information about the in-stream shared content served with the content; a companion shared content selection unit to select the companion shared content based on the monitored in-stream shared content and content, and the received information; and a transmitting unit to transmit the selected companion shared content to the online service.

Abstract: An access system for a vehicle may include a controller. The controller may be configured to respond to receiving an unlock signal indicative of an unlock request by causing a compartment closure to unlock for a predetermined time. Or the controller may be configured to respond to receiving an unlock signal indicative of an unlock request and a vehicle operation signal indicative of a vehicle secure state by causing a compartment closure to unlock for a predetermined time. Upon expiration of the predetermined time, the controller may cause the compartment closure to lock. The controller may be configured to respond to receiving an unlatch signal indicative of an unlatch request during the predetermined time by causing the compartment closure to unlatch.