Abstract: Information relating to project metric data and occurrence of events in a plurality of projects is received (102). Uncertainty data is determined (106) based on the received information, where the uncertainty data represents a probability distribution of at least one metric associated with the active project. Input relating to a scenario to perform what-if analysis is received (108), and based on the input, what-if analysis is performed (110).

Abstract: A system and an article of manufacture for providing a prompt for real-time cognitive assistance include analyzing input from at least one environmental sensor to identify context information pertaining to a user situation, identifying a likely subsequent cognitive task of the user in the user situation based on the context information and use of a learned model, determining an action with respect to information to be suggested to the user via a corresponding prompt, wherein the determining is based on the likely subsequent cognitive task, the context information and information learned from at least to one previous user situation, computing a confidence value to represent a level of certainty in the action, and providing the prompt to the user if the action has a confidence value greater than a threshold value corresponding to the action.

Abstract: A method is disclosed for operating a programmable logic controller which executes program(s) based on cycles having a predetermined cycle time in a predefined memory. An automated reasoning method based on an ontology and a description logic is implemented in the programmable logic controller. To enable this, at least the concepts and roles of the ontology are encoded using index numbers and the axioms of the ontology are encoded using tuples of integral index numbers. The automated reasoning method is interrupted before the end of a cycle and subsequently resumed at the current status of program execution. This allows for the cyclic programming paradigm of a programmable logic controller. The method can be used for any types of programmable logic controller, e.g., controllers of devices belonging to an automation system or energy generation devices. In such scenarios the automated reasoning method may be used for diagnosing the corresponding devices.

Abstract: Embodiments of the invention relate to a multiplexed neural core circuit. One embodiment comprises a neural core circuit including a memory device that maintains neuronal attributes for multiple neurons. The memory device has multiple entries. Each entry maintains neuronal attributes for a corresponding neuron. The core circuit further comprises a controller for managing the memory device and processing neuronal firing events targeting each neuron. The controller multiplexes computation and control logic for the neurons. In response to neuronal firing events targeting one of the neurons, the controller retrieves neuronal attributes for the target neuron from a corresponding entry of the memory device, and integrates the firing events based on the retrieved neuronal attributes to generate a firing event for the target neuron.

Abstract: A real-time system receives a selection structure formed by weighted rules joined by links, each of the weighted rules including a condition part, a conclusion part and a weight. The selection structure is an Algebraic Decision Diagram (ADD) that includes internal nodes, each representing a decision point and terminal nodes, each representing a subset of candidate results having an accumulated weight. In response to a query that specifies a set of conditions, the ADD is traversed by making a series of decisions at decision points of the ADD to reach at least one terminal node having a maximum accumulated weight among terminal nodes that satisfy the set of conditions. The subset of candidate results represented by the at least one terminal node is selected as the output for responding to the query.

Abstract: Mechanisms for recommending content items based on topics are provided. In some implementations, a method for recommending content items is provided that includes: determining a plurality of accessed content items associated with a user, wherein each of the plurality of content items is associated with a plurality of topics; determining the plurality of topics associated with each of the plurality of accessed content items; generating a model of user interests based on the plurality of topics, wherein the model implements a machine learning technique to determine a plurality of weights for assigning to each of the plurality of topics; applying the model to determine, for a plurality of content items, a probability that the user would watch a content item of the plurality of content items; ranking the plurality of content items based on the determined probabilities; and selecting a subset of the plurality of content items to recommend to the user based on the ranked content items.

Abstract: Embodiments of the invention relate to predicting user activity in a social media application. In one embodiment, user activity information is collected for a user from a social media application and activity features of the user are determined, based on the collected activity information for the user. Then a model is created to predict a future activity of the user in the social media application. The model uses the determined activity features of the user and results obtained from running the created model, to determine future activity of the user in the social media application.

Abstract: Systems and methods are disclosed to perform performance prediction for cloud-based databases by building on a computer a cloud database performance model using a set of training workloads; and using a learned model on the computer to predict database performance in the cloud for a new workload, wherein for each reference workload r and hardware configuration h, system throughput tr,h, average throughput of ?r and standard deviation ?r, comprising normalizing each throughput as: t r , h _ = t r , h - a r ? r .

Abstract: There is provided a method and system for modeling a data generating process. The method includes generating a dyadic Bayesian model including a pair of probabilistic functions representing a prior distribution and a sampling distribution, and modeling a data generating process based on the dyadic Bayesian model using observed data. The method includes generating a learner object for the dyadic Bayesian model. The method further includes training the dyadic Bayesian model with the learner object based on the observed data to produce a trained dyadic Bayesian model. The method also includes generating a posterior distribution over parameters based on the trained dyadic Bayesian model. The method also further includes generating a posterior predictive distribution based on the posterior distribution. The method also includes predicting an outcome of observable variables based on the posterior predictive distribution.

Abstract: A method, apparatus and product useful for classification reliability prediction. Utilize a separate classifier tool, referred to as a reliability classifier tool or RCT, in order to predict reliability of a prediction made by a classifier tool or CT by introducing additional features that were not used by the classifier tool itself.

Abstract: Common interests of at least two different groups of users are captured and analyzed to create a proposal for an event that would satisfy the interests of each group of users. One group of users may be consumers of content, another group of users may be providers of content and a further group of users may, for example, be venue providers. Once an event is proposed, ownership of the event may be prompted for.

Abstract: A processor based system and method of generating cognitive pattern knowledge of a sensory input is disclosed. The method comprising the steps of receiving sensory input to create at least one concrete pattern, receiving at least one abstract pattern comprising abstract segments and vertically blending the concrete pattern with the abstract pattern by selectively projecting abstract segments to create a vertically blended pattern whereby the vertically blended pattern represents cognitive pattern knowledge of the sensory input. In some embodiments, the systems and methods further comprise creating a measure of a degree of vertical blending and when the measure of the degree of vertical blending exceeds a threshold, horizontally blending at least two abstract patterns to create a horizontally blended abstract pattern.

Abstract: An approach is provided for identifying a solution to a problem where the problem and solution are in different disciplines. First data elements in common between first and second ontologies are determined and second data elements in common between first and third ontologies are determined. Based on the number of first data elements exceeding a threshold value and the number of second data elements not exceeding the threshold value, a bridged ontology is generated that merges the first and second ontologies but not the first and third ontologies. A relationship is identified between a subject, predicate and object extracted from a first data object which specifies the problem and, respectively, a subject, predicate, and object of a second data object included in the bridged ontology. Based on the relationship, the solution is identified as being the second data object.

Abstract: A complete end-to-end modeling system is provided that includes data sampling, feature engineering, action labeling, and model learning or learning from models built based on collected data. The end-to-end modeling process is performed via an automatic mechanism with minimal or reduced human intervention. A processor-readable medium is disclosed, storing processor-executable instructions to instantiate an automated data sampling and prediction structure training component, the automated data sampling and prediction structure training component being configured to automatically collect user event data samples, and use the collected user event data samples to train multiple prediction structures in parallel.

Abstract: Embodiments are directed towards generating application models based on discovery based machine learning. A mobile application may be uploaded to a computer that may be part of a testing platform. A reference mobile computer may be selected and the mobile application maybe installed onto the reference mobile computer. Also, the testing platform may generate an initial application model based on the mobile application. The current active window of the mobile application may be determined and the application model may be updated accordingly. Screenshots may be generated that correspond to each current active window of the mobile application. Also, each user-interface control in the active window may be activated. The results of activating each control may be observed and added to the model. If the activation causes navigation, another active window may be determined. The application model may be used for testing other mobile computers.

Abstract: A device, method and system for monitoring, predicting, and accelerating interactions with a computing device includes determining a current interaction context at a computing device based on interactions occurring at the computing device, predicting a number of potential subsequent interactions, speculatively executing at least some of the potential subsequent interactions, and presenting interactive representations of the speculatively-executed interactions at the computing device.

Abstract: A system and method for providing more than two levels of classification distinction of a user state are provided. The first and second general states of a user are sensed. The first general state is classified as either a first state or a second state, and the second general state is classified as either a third state or a fourth state. The user state of the user is then classified as one of at least three different classification states.

Abstract: Systems and methods are disclosed for more accurately estimating a remaining useful life (RUL) of an item. The RUL of the item is estimated by determining probability values throughout a time period. Each probability value quantifies a probability that a failure event of the item will occur by a time in a time segment of the time period. Based on the probability values, the particular time segment in which the failure event is most likely to occur is determined. Once the particular time segment is determined, the presentation of a visual representation of at least a portion of the time period can be effected. The visual representation indicates that the failure event of the item is most likely to occur during the particular time segment.

Abstract: Systems and methods for culture mapping and intelligence include software tools to collect, analyze, and categorize data based on behavior archetypes to produce information visualizations from the data. In one embodiment, a user query relative to a topic of interest may include a word, a combination of words, or a set of words for a particular field, such as a byline or hashtag of an online or networked community. One or more data sources, which may include social media and other websites are selected by the user or the system and a list of accounts ordered by one or more selected criteria, such as frequency of occurrence of the query words, for example, is produced. One or more weighting factors may then be associated with each account. A matrix is generated with accounts positioned to illustrate the account relative to behavior attributes along selected continuums.

Abstract: An apparatus, and related method, for identifying one or more association variables is described. The apparatus includes at least one processor, at least one memory, and at least one program module stored in the memory configured to be executed by the processor. The program module includes instructions for selecting a subset of temporal onsets in a set of temporal onsets, instructions for determining a statistical relationship between the subset and a pattern of occurrence of a variable, and instructions for identifying the variable as an association variable in accordance with the statistical relationship. The subset includes one or more first temporal onsets corresponding to one or more instances of an event, and the set of temporal onsets includes the subset of temporal onsets and one or more second temporal onsets corresponding to one or more instances of a reoccurrence event.