Abstract: A deep structured semantic module (DSSM) is described herein which uses a model that is discriminatively trained based on click-through data, e.g., such that a conditional likelihood of clicked documents, given respective queries, is maximized, and a condition likelihood of non-clicked documents, given the queries, is reduced. In operation, after training is complete, the DSSM maps an input item into an output item expressed in a semantic space, using the trained model. To facilitate training and runtime operation, a dimensionality-reduction module (DRM) can reduce the dimensionality of the input item that is fed to the DSSM. A search engine may use the above-summarized functionality to convert a query and a plurality of documents into the common semantic space, and then determine the similarity between the query and documents in the semantic space. The search engine may then rank the documents based, at least in part, on the similarity measures.

Abstract: A computing device trains models for streaming classification. A baseline penalty value is computed that is inversely proportional to a square of a maximum explanatory variable value. A set of penalty values is computed based on the baseline penalty value. For each penalty value of the set of penalty values, a classification type model is trained using the respective penalty value and the observation vectors to compute parameters that define a trained model, the classification type model is validated using the respective penalty value and the observation vectors to compute a validation criterion value that quantifies a validation error, and the validation criterion value, the respective penalty value, and the parameters that define a trained model are stored to the computer-readable medium. The classification type model is trained to predict the response variable value of each observation vector based on the respective explanatory variable value of each observation vector.

Abstract: A fabric selection tool provides an automated procedure for recommending and/or selecting a fabric for a window treatment to be installed in a building. The recommendation may be made to optimize the performance of the window treatment in which the fabric may be installed. The recommended fabric may be selected based on performance metrics associated with each fabric in an environment. The fabrics may be ranked based upon the performance metrics of one or more of the fabrics. One or more of the fabrics, and/or their corresponding ranks, may be displayed to a user for selection. The recommended fabrics may be determined based on combinations of fabrics that provide performance metrics for various façades of the building. Using the ranking system provided by the fabric selection tool, the user may obtain a fabric sample and/or order one or more of the recommended fabrics.

Abstract: A clustering coefficient-based adaptive clustering method, according to the categories of extracted data point pairs and the magnitude of association relations between data points extracted each time, determining to which category the data points belong, and the number of the categories, and establishing association relations between the data points and association relations between the categories; pre-segmenting each category and calculating the intra-category similarities of two sub-categories and inter-category similarities of the two sub-categories, judging whether the two pre-segmented sub-categories satisfy a segmentation condition, if so, then accepting the pre-segmentation; if not, then canceling the pre-segmentation; calculating the intra-category similarities and inter-category similarities of two categories having an association relation, judging whether the two categories satisfy a merging condition, if so, then merging the two categories to generate a new category; if not, then abandoning the mer

Abstract: A fabric selection tool provides an automated procedure for recommending and/or selecting a fabric for a window treatment to be installed in a building. The recommendation may be made to optimize the performance of the window treatment in which the fabric may be installed. The recommended fabric may be selected based on performance metrics associated with each fabric in an environment. The fabrics may be ranked based upon the performance metrics of one or more of the fabrics. One or more of the fabrics, and/or their corresponding ranks, may be displayed to a user for selection. The recommended fabrics may be determined based on combinations of fabrics that provide performance metrics for various façades of the building. Using the ranking system provided by the fabric selection tool, the user may obtain a fabric sample and/or order one or more of the recommended fabrics.

Abstract: A fabric selection tool provides an automated procedure for recommending and/or selecting a fabric for a window treatment to be installed in a building. The recommendation may be made to optimize the performance of the window treatment in which the fabric may be installed. The recommended fabric may be selected based on performance metrics associated with each fabric in an environment. The fabrics may be ranked based upon the performance metrics of one or more of the fabrics. One or more of the fabrics, and/or their corresponding ranks, may be displayed to a user for selection. The recommended fabrics may be determined based on combinations of fabrics that provide performance metrics for various façades of the building. Using the ranking system provided by the fabric selection tool, the user may obtain a fabric sample and/or order one or more of the recommended fabrics.

Abstract: A method for developing machine operation classifiers for a machine is disclosed. The method includes receiving training data associated with the machine from one or more on-board engineering channels associated with the machine and determining one or more training features based on the training data values. The method also includes determining one or more training labels associated with the one or more training features and building a predictive model for determining machine operation classifiers using a computer. Building the predictive model may include feeding the one or more training features and the one or more training labels associated with the one or more training features to a machine learning algorithm and determining a predictive model from the machine learning algorithm. The predictive model may be used for receiving new data associated with the machine and determining a predicted label based on the new data.

Abstract: Methods, systems and computer program products for resolving multiple magnitudes assigned to a target vector are disclosed. A target vector that includes one or more target vector dimensions is received. One of the target vector dimensions is processed to determine a total number of magnitudes assigned to the processed target vector dimension. Also, a source vector that includes one or more source vector dimensions is received. The received source vector is processed to determine a total number of features associated with the source vector. When it is detected that the total number of magnitudes assigned to the processed target vector dimension exceeds one, one of the assigned magnitudes is selected based on one of the determined features associated with the source vector.

Abstract: Methods and systems are provided for determining the location of procedure sites, for example hair implantation sites, the method and systems enabling a natural looking randomness to be maintained to achieve a desired density while avoiding previously created procedure sites and existing features.

Abstract: Systems and methods progressively or heuristically associate themes amongst plural objects in a computer setting. Objects, including files, modules, programs, data, and the like can be arranged in a population by their association with a particular theme and user-input context. Based on input search parameters and associations, the objects can be progressively matched with appropriate context and returned in more relevant searches. Themes and context for individual objects can be individually determined based on semantic input and well as meta data associated with the objects. Objects can be returned based on search criteria in rank order according to their association. Systems and methods are useable or organization of objects in Internet searches, document searches and collation, document and content visual representation, database management, polling systems, and document management systems.

Abstract: A machine learning heterogeneous edge device, method, and system are disclosed. In an example embodiment, an edge device includes a communication module, a data collection device, a memory, a machine learning module, a group determination module, and a leader election module. The edge device analyzes collected data with a model, outputs a result, and updates the model to create a local model. The edge device communicates with other edge devices in a heterogeneous group. The edge device determines group membership and determines a leader edge device. The edge device receives a request for the local model, transmits the local model to the leader edge device, receives a mixed model created by the leader edge device performing a mix operation of the local model and a different local model, and replaces the local model with the mixed model.

Abstract: Anomalies in real time series are detected by first determining a similarity matrix of pairwise similarities between pairs of normal time series data. A spectral clustering procedure is applied to the similarity matrix to partition variables representing dimensions of the time series data into mutually exclusive groups. A model of normal behavior is estimated for each group. Then, for the real time series data, an anomaly score is determined, using the model for each group, and the anomaly score is compared to a predetermined threshold to signal the anomaly.

Abstract: A system for automatically automatic workflow triggering using real-time analytics, comprising an analytics server that receives and analyzes interaction information and a workflow server that produces workflow events based on the analysis, sends workflow events to handlers for processing, retrieves workflow-related data, and produces workflow reports for review, and a method for automatically automatic workflow triggering using real-time analytics.

Abstract: There is provided systems and methods for generating suggestions integrated into business applications. Parameters for generating suggestions relating to the plurality of business applications are stored in a dynamic database. At least one suggestion relating to a business currently being used by a user is generated, the at least one suggestion generated using the parameters stored in the dynamic database. The at least one suggestion is integrated into the user interface of the given business application. Input of the user into the given business application is monitored, including input reflecting whether the at least one suggestion has been actioned by the user; and the parameters stored in the dynamic database are updated based on the monitored input so that generation of future suggestions may be refined.

Abstract: The embodiment of this disclosure may include a rule engine that adds a plurality of objects into a working memory, and processes the plurality of objects through a plurality of rules stored in a rule repository. Then, the rule engine may create a rule network comprising a root node and a child node based on the plurality of rules, and associate the root node with a predetermined list of object references. The rule engine may build a multi-object sub-token based on the plurality of objects that satisfy the predetermined list of object references. Then, the rule engine may pass the multi-object sub-token from the root node to the child node.

Abstract: Features are disclosed for predicting or otherwise determining when a user will initiate an operation on a user computing device, such as requesting network-accessible content. Upon making the determination, the user computing device can proactively perform the determined operation or portions thereof. The user computing device may use a detection model or profile that associates user-initiated operations with data from sensors on the user computing device. The sensors may include movement sensors, environmental sensors, and the like. One benefit, among others, is that user-perceived performance can be improved because some or all of a user-initiated operation has been performed prior to user-initiation of the operation.

Abstract: Embodiments of the invention provide a method comprising creating a structural description for at least one neurosynaptic core circuit. Each core circuit comprises an interconnect network including plural electronic synapses for interconnecting one or more electronic neurons with one or more electronic axons. The structural description defines a desired neuronal activity for the core circuits. The desired neuronal activity is simulated by programming the core circuits with the structural description. The structural description controls routing of neuronal firing events for the core circuits.

Abstract: Historical context information that includes data from communications of one or more mobile devices is collected. The historical context information includes at least one of communication environment, communication parameter estimates, mobile device statistics, mobile device transmit settings, base station receiver settings, past network statistics and settings, and adjacent network node information statistics and settings. A predictive model for network communications is determined based on the historical context information. A communication context for a first mobile device different than the one or more mobile devices is determined. The first device is scheduled and/or network parameters are set based on the determined predictive model. Actual results are compared to expected results and the predictive model is adjusted based on the comparison.

Abstract: Systems and methods for determining well parameters for optimization of well performance. The method includes training, via a computing system, a well performance predictor based on field data corresponding to a hydrocarbon field in which a well is to be drilled. The method also includes generating, via the computing system, a number of candidate well parameter combinations for the well and predicting, via the computing system, a performance of the well for each candidate well parameter combination using the trained well performance predictor. The method further includes determining, via the computing system, an optimized well parameter combination for the well such that the predicted performance of the well is maximized.

Abstract: To suggest new connections to a user of a social networking system, the system generates a set of candidate users to whom the user has not already formed a connection. The system determines the likelihood that the user will connect to each candidate user if suggested to do so, and it also computes the value to the social networking system if the user does connect to the candidate user. Then, the system computes an expected value score for each candidate user based on the corresponding likelihood and the value. The candidate users are ranked and the suggestions are provided to the user based on the candidate users' expected value scores. The social networking system can suggest other actions to a user in addition to forming a new connection with other users.