Abstract: A calculation apparatus includes a feature vector acquisition unit for acquiring a feature vector that corresponds to each alternative of a plurality of choice sets; an absolute evaluation calculation unit for calculating an absolute evaluation vector that represents an absolute evaluation of alternatives independent of a combination of the plurality of alternatives; a relativized-matrix calculation unit for calculating a relativized matrix that represents relative evaluations of the plurality of alternatives in a choice set; and a relative evaluation calculation unit for calculating a relative evaluation vector that represents a relative evaluation of each alternative of the plurality of alternatives from a product of multiplying the relativized matrix by the absolute evaluation vector. The calculation apparatus can predict intransitive choices of a person who exhibits intransitive preferences.

Abstract: The disclosed embodiments provide a system for facilitating sentiment analysis. During operation, the system obtains a set of training data that includes a first set of content items containing words associated with a domain, a set of sentiment scores for the first set of content items, and a set of outcomes associated with the first set of content items. Next, the system uses the training data to train a statistical model for performing sentiment analysis that is specific to the domain. The system then enables use of the statistical model in generating a set of domain-specific sentiment scores for a second set of content items containing words associated with the domain.

Abstract: Approaches presented herein enable intelligent service request classification and assignment learning. More specifically, a request comprising a free form text or spoken description is received from a user. The request description is parsed and classified by a regression-based classifier. The regression-based classifier classifies based on, for example: the description itself; the requestor's history of requests, and/or supplemental demographics about a requestor. Optionally, a user may verify the classification or select from a plurality of returned classifications. A service provider or administrator confirms that a classification is correct. If not, the incorrectly classified request is queued. If so, the correctly classified request is added to a set of training data to be used in classifying future requests.

Abstract: Disclosed systems, methods, and computer readable media can detect an association between semantic entities and generate semantic information between entities. For example, semantic entities and associated semantic collections present in knowledge bases can be identified. A time period can be determined and divided into time slices. For each time slice, word embeddings for the identified semantic entities can be generated; a first semantic association strength between a first semantic entity input and a second semantic entity input can be determined; and a second semantic association strength between the first semantic entity input and semantic entities associated with a semantic collection that is associated with the second semantic entity can be determined. An output can be provided based on the first and second semantic association strengths.

Abstract: A method of operating a neural network includes determining a complexity, such as a number) of separable filters approximating a filter. The method further includes selectively applying a decomposed convolution to the filter based on the determined number of separable filters.

Abstract: A method and apparatus enables identification of customer characteristics and behavior, and predicts the customer's intent. Such prediction can be used to adopt various business strategies to increase the chances of conversion of customer interaction to a sale, and thereby can increase revenue, and/or enhance the customer's experience.

Abstract: A system and method to accurately modify the function of a user's electronic device in response to the multiple aspects making up a user's evolving state of mind are presented. Persistent intent objects are generated to represent a user's state of mind and the relative importance of a particular state of mind to a user's instant attention. The intent objects can be related to situations or environments and could exist beyond any specific situations or environments. The collective effect of the intent objects can be used to customize the functions of a user device to match the user's state of mind extending beyond inferences drawn from an individual or instant set of circumstances.

Abstract: Embodiments of the present invention relate to providing business customers with predictive capabilities, such as identifying valuable customers or estimating the likelihood that a product will be purchased. An adaptive sampling scheme is utilized, which helps generate sample data points from large scale data that is imbalanced (for example, digital website traffic with hundreds of millions of visitors but only a small portion of them are of interest). In embodiments, a stream of sample data points is received. Positive samples are added to a positive list until the desired number of positives is reached and negative samples are added to a negative list until the desired number of negative samples is reached. The positive list and the negative list can then be combined, shuffled, and fed into a prediction model.

Abstract: A system for self-adaptive user reading preference learning and screen layout optimization for multi-media information is disclosed. The system is particular useful for devices with small display form factors, such as mobile devices. Data flow diagram (DFD) technique is used to represent a model of the screen layout for visualization. The system processes input information, which includes user information, device information, context information, and the news. The delivery news is filtered in the news processing system and presented to a user based the user's interest, whereas device information and context information, are also factors that take effect in the modeling.

Abstract: A system is provided for maintenance of a manufactured product composed of a plurality of parts. A modeling engine may receive failure data for the plurality of parts in which the failure data indicates individual instances of failure of at least two of a multiple quantity of a part of the plurality of parts. Each of the at least two of the multiple quantity may be located at a respective distinct location in the manufactured product. The modeling engine may generate a superimposed failure model (SFM) for the part, including determining a lifetime distribution of the part based at least partially on application of a lifetime distribution model to the SFM. A maintenance engine coupled to the modeling engine may perform a maintenance activity including determining a maintenance interval determined for the part according to the lifetime distribution of the part.

Abstract: A method for wastewater treatment that comprises receiving influent readings from sensors located along influent stream(s) of a wastewater treatment unit, effluent readings from sensors located along effluent stream(s) of the wastewater treatment unit, a feedback flow variable calculated according to a state of a feedback flow channel between an effluent output and an influent input, analyzing the influent readings and the effluent readings to extract an influent flow variable, a total nitrogen at effluent variable and a total phosphorus at effluent variable, and calculating control instructions to control the wastewater treatment unit by assigning a combination of a cost variable reflecting a treatment cost for treating the influent stream(s), a time period, the influent flow variable, the total nitrogen at effluent variable, the total phosphorus at effluent variable, and the feedback flow variable in a state space of the wastewater treatment unit.

Abstract: An apparatus for recognizing a representative user behavior includes a unit-data extracting unit configured to extract at least one unit data from sensor data, a feature-information extracting unit configured to extract feature information from each of the at least one unit data, a unit-behavior recognizing unit configured to recognize a respective unit behavior for each of the at least one unit data based on the feature information, and a representative-behavior recognizing unit configured to recognize at least one representative behavior based on the respective unit behavior recognized for each of the at least one unit data.

Abstract: A method for improving performance of a trained machine learning model includes adding a second classifier with a second objective function to a first classifier with a first objective function. Rather than minimizing a function of errors for the first classifier, the second objective function is used to directly reduce the number errors of the first classifier.

Abstract: In some embodiments, the present invention provides for a computer system which includes a content database storing initial content data and a vocabulary data set; a processor configured to applying a machine learning model to transform the initial content data into a N-dimensional vector space; self-training the machine learning model based on the vocabulary data set; applying a clustering technique to the N-dimensional vector space to generate a cluster model of clusters, where each cluster includes a plurality of word representations; associating each cluster with a cluster identifier; obtaining subsequent content data; associating each data element of the subsequent content data with each cluster to generate a content data cluster mapping model; continuously tracking, for each user, each respective cluster identifier of each respective cluster associated with each action performed by each user with each data element to continuously self-adapt each user-specific, time-specific dynamic cluster mapping model

Abstract: Corresponding to each forecasting model of a family of related models for a time series sequence, a respective state space representation is generated. One or more cross-validation iterations are then executed for each model of the family. In a given iteration, a training variant of the time series sequence is generated, with a subset of the time series sequence entries replaced by representations of missing values. Predictions for the missing values are obtained using the state space representation and the training variant, and a model quality metric is obtained based on prediction errors. The optimal model of the family is selected using the model quality metrics obtained from the cross validation iterations.

Abstract: Systems, methods and aspects, and embodiments thereof relate to unsupervised or semi-supervised features learning using a quantum processor. To achieve unsupervised or semi-supervised features learning, the quantum processor is programmed to achieve Hierarchal Deep Learning (referred to as HDL) over one or more data sets. Systems and methods search for, parse, and detect maximally repeating patterns in one or more data sets or across data or data sets. Embodiments and aspects regard using sparse coding to detect maximally repeating patterns in or across data. Examples of sparse coding include L0 and L1 sparse coding. Some implementations may involve appending, incorporating or attaching labels to dictionary elements, or constituent elements of one or more dictionaries. There may be a logical association between label and the element labeled such that the process of unsupervised or semi-supervised feature learning spans both the elements and the incorporated, attached or appended label.

Abstract: The present disclosure is directed towards systems and methods for improving anomaly detection using injected outliers. A normalcy calculator of a device may include a set of outliers into a training dataset of data points. The normalcy calculator, using a K-means clustering algorithm applied on the training dataset, identify at least a first cluster of data points. The normalcy calculator of the device may determine a region with a center and an outer radius that covers at least a spatial extent of the first cluster of data points. The normalcy calculator may determine a first normalcy radius for the first cluster by reducing the region around the center until a point at which all artificial outliers are excluded from a region defined by the first normalcy radius. An outlier detector of the device may use the region defined by the first normalcy radius to determine whether a new data point is normal or abnormal.

Abstract: Enhancement of a first mind map to become a second enhanced mind includes: providing a content pool with information items; performing a first semantic scan based on a selected object; and generating a new object and a related connection to the selected object based on the semantic scan. Furthermore, the enhancement includes determining a strength value for each of the connections of the first mind map and determining the connection with the lowest strength value and recalculating the strength value using an external knowledge base to define the connection as obsolete if the strength value decreases.

Abstract: Mechanisms are provided for implementing a virtual corpus engine that receives an inquiry to be processed and analyzes the inquiry to extract one or more features of the inquiry. The virtual corpus engine selects a weight matrix associated with a virtual corpus based on the extracted one or more features of the inquiry. The virtual corpus comprises a plurality of actual corpora of information. The weight matrix comprises a separate weight value for each actual corpus in the plurality of actual corpora. The virtual corpus engine processes the inquiry using a set of selected actual corpora selected from the plurality of actual corpora based on the weight values in the weight matrix and receives results of the processing of the inquiry using the set of selected actual corpora. The virtual corpus engine outputs the results of the processing of the inquiry.

Abstract: Systems and methods of embodiments comprise receiving in real-time data of parameters representing an entity. Micro plots are generated, and each micro plot comprises a plot of the data for a corresponding time period of a multitude of time periods. Each time period is cyclical. A model plot is generated to include the micro plots plotted chronologically according to the time periods. The model plot comprises a continuous helix. A prediction of a state of the entity is generated using characteristics of the model plot.