Thu, 03 Nov 2016 08:00:00 EDTIn one implementation, a method includes obtaining time series data. The time serious data includes a plurality of network utilization measurements. The plurality of network utilization measurements is indicative of a plurality of utilizations of one or more resources of a network resource at a plurality of times. The method also includes determining whether the time series data comprises a plurality of segments. Each segment of the plurality of segments is associated with a separate regression model and each segment includes a portion of the time series data. The method further includes identifying a current segment from the time series data when the time series data comprises the plurality of segments. The method further includes determining an estimated network utilization based on a current regression model associated with the current segment.
Thu, 03 Nov 2016 08:00:00 EDTAn operational parameter value learning device according to one embodiment learns an operational parameter value of a device for each of users. A calculator is configured to calculate a duration time during which the device is estimated to have operated at each operational parameter value for each of the users based on history information including at least one of: behavior states of the users, an environmental state, and an operational state of the device. A selector is configured to calculate a continuation probability feature amount according to which the device continues an operation at each operational parameter value in each duration time for each of the users on a basis of the duration time calculated by calculator and selects the operational parameter value based on the calculated continuation probability feature amount.
Thu, 03 Nov 2016 08:00:00 EDTAn optimized artificial intelligence machine may: receive information indicative of the times, locations, and types of crimes that were committed over a period of time in a geographic area; receive information indicative of the number and locations of patrol agents that were patrolling during the period of time; build a learning model based on the received information that learns the relationships between the locations of the patrol agents and the crimes that were committed; and determine whether and where criminals would commit new crimes based on the learning model and a different number of patrol agents or locations of patrol agents. The optimized artificial intelligence machine may determine an optimum location of a pre-determined number of patrolling agents to minimize the number or seriousness of crimes in a geographic area based on the learned model of the relationships between the locations of the patrol agents and the crimes that were committed, and may automatically activate or position one or more of the patrolling agents in accordance with the determination.
Thu, 03 Nov 2016 08:00:00 EDTTechniques are described herein for classifying an electronic message with a particular project from among a plurality of projects. In some embodiments, first and second users associated with the electronic message are identified, and one or more first projects associated with the first user and one and more second projects associated with the second user are determined. Projects that are in common between the first projects and the second projects are determined. When only a single project is in common, the electronic message is associated with the single project. When more than a single project is in common, features associated with each of the projects found to be in common are analyzed by a machine learning model to determine the most likely project to associate with the electronic message from among the projects found to be in common.
Thu, 03 Nov 2016 08:00:00 EDTClassifier generation methods are described in which features used in classification (e.g., mass spectral peaks) are selected, or deselected using bagged filtering. A development sample set is split into two subsets, one of which is used as a training set the other of which is set aside. We define a classifier (e.g., K-nearest neighbor, decision tree, margin-based classifier or other) using the training subset and at least one of the features (or subsets of two or more features in combination). We apply the classifier to a subset of samples. A filter is applied to the performance of the classifier on the sample subset and the at least one feature is added to a “filtered feature list” if the classifier performance passes the filter. We do this for many different realizations of the separation of the development sample set into two subsets, and, for each realization, different features or sets of features in combination. After all the iterations are performed the filtered feature list is used to either select features, or deselect features, for a final classifier.
Thu, 03 Nov 2016 08:00:00 EDTAn opportunity surfacing architecture for surfacing an opportunity to a user in a computing system comprises, in one example, a user interface component and a machine learning framework configured to detect first inputs indicative of an opportunity performance history of a user and to detect second inputs indicative of a new opportunity. The machine learning framework is configured to generate a user-specific indicator for the new opportunity based on the opportunity performance history. The opportunity surfacing architecture comprises an opportunity surfacing system configured to control the user interface component to generate a user interface display that displays a representation of the new opportunity to the user based on the user-specific indicator.
Thu, 03 Nov 2016 08:00:00 EDTSystems, 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.
Thu, 03 Nov 2016 08:00:00 EDTDetecting patterns and sequences associated with an anomaly in predictions made a predictive system. The predictive system makes predictions by learning spatial patterns and temporal sequences in an input data that change over time. As the input data is received, the predictive system generates a series of predictions based on the input data. Each prediction is compared with corresponding actual value or state. If the prediction does not match or deviates significantly from the actual value or state, an anomaly is identified for further analysis. A corresponding state or a series of states of the predictive system before or at the time of prediction are associated with the anomaly and stored. The anomaly can be detected by monitoring whether the predictive system is placed in the state or states that is the same or similar to the stored state or states.
Thu, 03 Nov 2016 08:00:00 EDTA mechanism is provided in a data processing system for determining comprehensiveness of a question paper given a syllabus of topics. An answer and evidence generator of a question answering system executing on the data processing system finds one or more answers based on the syllabus of topics for each question in the question paper. The answer and evidence generator identifies evidence for the one or more answers in the syllabus for each question in the question paper. A concept identifier of the question answering system identifies a set of concepts in the syllabus corresponding to the evidence for each question in the question paper to form a plurality of sets of concepts. The mechanism determines a value for a comprehensiveness metric for the question paper with respect to the syllabus of topics based on the plurality of sets of concepts.
Thu, 03 Nov 2016 08:00:00 EDTIn some examples, systems and techniques can determine a respective visit likelihood for each respective destination of a plurality of destinations based at least in part on a respective distance between the respective destination and a geographic location from a location history associated with a user and a comparison between a time associated with the geographic location and a visit likelihood distribution across time. The systems and techniques can then sort at least some of the plurality of destinations. In other examples, systems and techniques can determine whether a user is likely to visit a place during a future instance of a timeslot based at least in part on a location history associated with the user. The systems and techniques can then output information relating to the place prior to the beginning of the future instance of the timeslot.
Thu, 03 Nov 2016 08:00:00 EDTA method, system, and computer program product for managing resources by obtaining a high spatial resolution estimate of behavior adoption are described. The method includes obtaining a low-resolution estimate with a fixed geographic scale, selecting a sample of customers based on the low-resolution estimate, implementing a statistical model to obtain relative probability of adoption of the behavior by each of the sample of customers, and generating a weighted random realization from the sample of customers, the weighted random realization being weighted based on the relative probability of adoption. The method includes iteratively implementing the selecting the sample of customers, the implementing the statistical model, and the generating the weighted random realization to obtain a set of the weighted random realizations, and obtaining the high spatial resolution estimate, providing greater resolution than the low-resolution estimate at a location of interest, based on the set of the weighted random realizations.
Thu, 03 Nov 2016 08:00:00 EDTAutomatic recognition and presentation of insights of data is provided through analysis of overall data to infer locations of a user's data. Statistical, heuristic, and comparable analysis on the user's data sets is used to determine insights such as trends, correlations, outliers, comparisons, and patterns. The insights are then presented to the user through automatically optimized visualizations (highlighting determined insights), emphasis on presented raw data, data formatting suggestions, and similar ones with the capability to explore further.
Thu, 03 Nov 2016 08:00:00 EDTAspects of the technology described herein provide a personalized computing experience for a user based on a predicted future semantic location of the user. In particular, a likely future location (or sequences of future locations) for a user may be determined, including contextual information about the future location. Using information from the current context of the user's current location with historical observations about the user and expected user events, out-of-routine events, or other lasting or ephemeral information, a prediction of one or more future semantic locations and corresponding confidences may be determined and used for providing personalized computing services to the user. The prediction may be provided to an application or service such as a personal assistant service associated with the user, or may be provided as an API to facilitate consumption of the prediction information by an application or service.
Thu, 03 Nov 2016 08:00:00 EDTAccording to an embodiment, a lattice finalization device finalizes a portion of a lattice that is generated by pattern recognition with respect to a signal on a frame-by-frame basis in chronological order. The device includes a detector and a finalizer. The detector is configured to detect, as a splitting position, a frame in the lattice in which the number of nodes and passing arcs is equal to or smaller than a reference value set in advance. The finalizer is configured to finalize nodes and arcs in paths from a start node to the splitting position in the lattice.
Thu, 03 Nov 2016 08:00:00 EDTThe disclosure is directed to evaluating feature vectors using decision trees. Typically, the number of feature vectors and the number of decision trees are very high, which prevents loading them into a processor cache. The feature vectors are evaluated by processing the feature vectors across a disjoint subset of trees repeatedly. After loading the feature vectors into the cache, they are evaluated across a first subset of trees, then across a second subset of trees and so on. If the values based on the first and second subsets satisfy a specified criterion, further evaluation of the feature vectors across the remaining of the decision trees is terminated, thereby minimizing the number of trees evaluated and therefore, consumption of computing resources.
Thu, 03 Nov 2016 08:00:00 EDTA computer receives information detailing the wardrobe of the user, including apparel and accessories, stored in a wardrobe database. The computer receives the schedule of the user and searches the schedule for keywords associated with dress codes and locational information in order to identify the dress code and locations of scheduled events. The computer cross references the determined dress code and weather conditions with suitable clothing in the wardrobe of the user then sends a signal to receivers in the wardrobe to indicate to the user which articles of clothing are appropriate for the weather and occasions of a particular day.
Thu, 03 Nov 2016 08:00:00 EDTThe invention relates to a method to determine a formula for a sample color matching a target color, based on an obsolete color formula, based on a given range of tinting bases. According to the proposed method, a color prediction model is used to calculate a distance between respective color parameters of a candidate color formula and the color parameters of the target color, and a genetic algorithm is used to obtain the formula for the sample color out of a population of candidate color formulas, wherein a distance of respective color parameters of a candidate color formula of the population of candidate color formulas to the color parameters of the target color is minimized by the genetic algorithm by iterative steps of mutation/crossing-over and selection of candidate color formulas that fit best to a fitness criterion, until a pre-given stopping criterion is fulfilled which automatically leads to a candidate color formula which is kept as the sample color formula.
Thu, 03 Nov 2016 08:00:00 EDTA method for predicting an interface control action of a user with an in-vehicle user interface involves collecting and storing data. The data can be vehicle data about the vehicle and its environment collected from at least one sensor of the vehicle and user data about user interactions with the user interface and/or different applications inside the vehicle. Likelihoods are assigned to at least two possible interface control actions by the user based on the collected and stored data. At least one most likely interface control action is determined from the likelihoods and the user is presented with the at least one most likely interface control action so that it is selectable and performable with one single user interaction with the user interface.
Thu, 03 Nov 2016 08:00:00 EDTA mechanism is provided for identifying a set of top-m clusters from a set of top-k plans. A planning problem and an integer value k indicating a number of top plans to be identified are received. A set of top-k plans are generated with at most size k, where the set of top-k plans is with respect to a given measure of plan quality. Each plan in the set of top-k plans is clustered based on a similarity between plans such that each cluster contains similar plans and each plan is grouped only into one cluster thereby forming the set of top-m clusters. A representative plan from each top-m cluster is presented to the user.
Thu, 03 Nov 2016 08:00:00 EDTA computing system includes technologies for providing trusted predictive analytics services. The computing system provides a common description language for predictive analytics services, and uses cryptographic techniques and digital rights management techniques to protect input data and/or portions of the predictive analytics services.
Thu, 03 Nov 2016 08:00:00 EDTA method of biasing a deep neural network includes determining whether an element has an increased probability of being present in an input to the network. The method also includes adjusting a bias of activation functions of neurons in the network to increase sensitivity to the element. In one configuration, the bias is adjusted without adjusting weights of the network. The method further includes adjusting an output of the network based on the biasing.
Thu, 03 Nov 2016 08:00:00 EDTAn information processing method and apparatus, the method including: training a Deep Neural Network (DNN) by using an evaluation object seed, an evaluation term seed and an evaluation relationship seed (101); at a first input layer, connecting vectors corresponding to a candidate evaluation object, a candidate evaluation term and a candidate evaluation relationship to obtain a first input vector (102); at a first hidden layer, compressing the first input vector to obtain a first middle vector, and at a first output layer, decoding the first middle vector to obtain a first output vector (103); and determining a first output vector whose decoding error value is less than a decoding error value threshold, and determining a candidate evaluation object, a candidate evaluation term and a candidate evaluation relationship corresponding to the determined first output vector as first opinion information (104). By use of the technical solution, precision of extracting opinion information from an evaluation text can be enhanced.
Thu, 03 Nov 2016 08:00:00 EDTA method of training a neural network model includes determining a specificity of multiple filters after a predetermined number of training iterations. The method also includes training each of the filters based on the specificity.
Thu, 03 Nov 2016 08:00:00 EDTThe present invention provides a system comprising multiple core circuits. Each core circuit comprises multiple electronic axons for receiving event packets, multiple electronic neurons for generating event packets, and a fanout crossbar including multiple electronic synapse devices for interconnecting the neurons with the axons. The system further comprises a routing system for routing event packets between the core circuits. The routing system virtually connects each neuron with one or more programmable target axons for the neuron by routing each event packet generated by the neuron to the target axons. Each target axon for each neuron of each core circuit is an axon located on the same core circuit as, or a different core circuit than, the neuron.
Thu, 03 Nov 2016 08:00:00 EDTA pattern recognition system having a plurality of sensors, a plurality of first activation cells wherein ones of the first activation cells are connected to one or more of the sensors, a plurality of second activation cells, wherein overlapping subsets of the first activation cells are connected to ones of the second activation cells, and an output for summing at least outputs from a subset of the plurality of second activation cells to produce a result.
Thu, 03 Nov 2016 08:00:00 EDTEmbodiments of the invention relate to a neural network circuit comprising a memory block for maintaining neuronal data for multiple neurons, a scheduler for maintaining incoming firing events targeting the neurons, and a computational logic unit for updating the neuronal data for the neurons by processing the firing events. The network circuit further comprises at least one permutation logic unit enabling data exchange between the computational logic unit and at least one of the memory block and the scheduler. The network circuit further comprises a controller for controlling the computational logic unit, the memory block, the scheduler, and each permutation logic unit.
Thu, 03 Nov 2016 08:00:00 EDTA method for providing interaction over a communication network between a user and network entities are described. The method includes at the interface apparatus end, adjusting the interface apparatus to operating conditions of the communication network, including network availability, and reconfiguring and controlling functionality of the network entities for adjusting operation of the network entities to predetermined requirements imposed on the external entities for cooperation with the interface apparatus. The method further includes receiving verbal and visual user input information and user state information related to a state of the user from the user; processing the obtained input information and forwarding the corresponding processed signal to one or more network entities. The method also includes receiving coded information output signals from one or more network entities, and processing thereof to obtain user information output signals in a format suitable for outputting to the user.
Thu, 03 Nov 2016 08:00:00 EDTA method of assessing chemical products includes: receiving input data including identification of a chemical substance at a processing device; evaluating a regulatory impact of the chemical substance based on at least one of global regulation data, regional regulation data and jurisdiction-specific regulation data, and outputting a regulatory impact assessment; evaluating potential hazards posed by the chemical substance based on available data related to characteristics of the chemical substance by comparing the characteristics to a plurality of criteria including environmental criteria, toxicity criteria related to effects on human health, and physical criteria related to hazards encountered during material transportation and handling, and outputting a chemical hazard assessment; and generating a chemical assessment report indicating potential impact due to use of the chemical substance, the chemical assessment report indicating chemical assessment results that include the regulatory impact assessment and the chemical hazard assessment.
Thu, 03 Nov 2016 08:00:00 EDTAn advice system employs a genetic analysis of a patient to identify one or more characteristics of the patient. The advice system employs the characteristics to identify one or more attributes of a medical device that would desirably exist in a medical device that is to be prescribed for the patient. The advice system then identifies from the one or more attributes one or more medical devices from among a plurality of medical devices whose features at least in part meet the one or more attributes. The advice system then outputs a recommendation of the one or more medical devices. The system employs known genes that are expressive of certain traits in a person, with the known traits being interpreted or evaluated in terms of characteristics that are relevant in selecting a medical device from among a plurality of medical devices, such as patient interface devices or other devices.
Thu, 03 Nov 2016 08:00:00 EDTMethods and apparatus, including computer program products, implementing and using techniques for text analysis of medical study data to extract predictive data. Natural language processing is performed on a document in a collection of documents to determine whether the document contains medical model data. In response to determining that the document contains medical model data, content relating to the medical model data in the document is annotated. A first medical model is generated based on the annotations for the identified medical model data and a certainty threshold In response to the certainty threshold meeting a user setting, the first medical model is added to a predictive model for determining a risk score, based on the analyzed data.
Thu, 03 Nov 2016 08:00:00 EDTSystems and methods are disclosed for determining individual-specific blood flow characteristics. One method includes acquiring, for each of a plurality of individuals, individual-specific anatomic data and blood flow characteristics of at least part of the individual's vascular system; executing a machine learning algorithm on the individual—specific anatomic data and blood flow characteristics for each of the plurality of individuals; relating, based on the executed machine learning algorithm, each individual's individual-specific anatomic data to functional estimates of blood flow characteristics; acquiring, for an individual and individual-specific anatomic data of at least part of the individual's vascular system; and for at least one point in the individual's individual-specific anatomic data, determining a blood flow characteristic of the individual, using relations from the step of relating individual-specific anatomic data to functional estimates of blood flow characteristics.
Thu, 03 Nov 2016 08:00:00 EDTA framework diagnostic test planning is described herein. In accordance with one aspect, the framework receives data representing one or more sample patients, diagnostic tests administered to the one or more sample patients, diagnostic test results and confirmed medical conditions associated with the administered diagnostic tests. The framework trains one or more classifiers based on the data to identify diagnostic test plans from the diagnostic tests. The one or more classifiers may then be applied to current patient data to generate a diagnostic test plan for a given patient.
Thu, 03 Nov 2016 08:00:00 EDTIn one embodiment, a translation system may use a translation bug prediction model to more efficiently identify translation errors in a user interface text string. The translation system may apply a translation bug prediction model to a translation resource to identify a potential error source. The translation system may associate an attention flag with the translation resource when identified as the potential error source. The translation system may execute an automatic translation of the translation resource to create a translation target.
Thu, 03 Nov 2016 08:00:00 EDTWe have developed a novel AKI diagnostic algorithm upon KID 2009 database. The KID is multi-featured and the AKI and non-AKI groups are highly imbalanced, making it challenging to describe them via simple linear statistics. Thus, to identify features effectively, our AKI association studies employed statistical learning strategies; a predictive model was created to accurately determine which KID data elements were highly associated with an AKI diagnosis. We employed prediction analysis of microarrays (PAM), which is commonly applied to high-feature datasets such as DNA microarrays; PAM determines which data elements, or features, best contribute to the predictive model or characterize individual classes/cohorts, Clinical Classification Software codes (286 diagnosis, 231 procedural) were used to bin ICD-9-CM codes (n=6,722) and analyzed by PAM. PAM identified relevant AKI predictors and eliminated irrelevant data elements, which constitute noise.