Abstract: In one advantageous embodiment, a method is provided for managing data. Information about the plurality of components is identified using data to form a plurality of instances for a plurality of nodes in response to receiving data for a plurality of components. Each node in the plurality of nodes corresponds to a component in the plurality of components. A number of variables having a range of values are formed to form a data structure. Each value in the range of values indicates a point in time at which a change to the information for a node occurs between a first instance and a second instance in the plurality of instances. More than one change between two consecutive instances is absent. The data structure is used to identify probability information about the plurality of components associated with the plurality of nodes.

Abstract: A method for providing a response to a statement of a user, the method includes: receiving user input that comprises a portion of a user statement; selecting, before receiving a whole user statement, an answerable statement response between an answerable statement, multiple answerable statements and a response to an answerable statement; wherein the selecting is responsive to user input and to structured representations of answerable statements answerable by an answering entity; and sending to the user information representative of response to the user statement.

Abstract: Techniques are disclosed for using atomic agents to implement modifications to actors. The atomic agents are self-functioning and may be applied to and removed from an actor in order to modify the behavior and/or appearance of the actor. The default appearance and behavior of the actor is embedded in the program code that defines the actor. One or more atomic agents may be applied to the actor to modify the actor's appearance or behavior without requiring any communication or interaction with the program code that defines the actor. Separate program code defines each atomic agent and the compatibility between the respective atomic agent and other atomic agents.

Abstract: A system, method and program product training and verifying using an identity or entity model. A training system is disclosed that includes: a feature correlation system that groups features from an inputted feature data sample into subsets; a plurality of classifiers that determine if each feature classifies into an associated one of a plurality of feature models that make up the entity model; and a boosting system that boosts features from a subset for a next round of training if any of the features classify and at least one correlated feature from the subset does not classify.

Abstract: Processing transactions using graph-based computations includes determining that at least one of a plurality of graph elements of a computation graph of a set of one or more computation graphs includes a computation to be performed for a given transaction, associating the given transaction with an instance of the computation graph that includes reusable computation elements associated with respective graph elements, and executing the graph to perform the computation.

Abstract: A system for generating a demographic profile for a set of at least one webpage, the system comprising a webpage audience information gatherer operative for providing, for at least one webpage, training data including demographic information characterizing an audience of the webpage; a predictor developing system operative to compute at least one content characteristic of said webpage and to develop a prediction process which if applied to said content characteristic would have predicted said training data; and a webpage audience predictor operative, for at least one new webpage, whose audience is unknown, to compute at least one content characteristic of the new webpage and to generate predicted demographic information predicted to characterize said unknown audience of said new webpage by applying said prediction process to said new webpage's content characteristic.

Abstract: A system, method and computer program product produce spike-dependent plasticity in an artificial synapse. A method includes: an electronic device generating a pre-synaptic pulse that occurs a predetermined period of time after receiving a pre-synaptic spike at a first input. The electronic device generating a post-synaptic pulse that starts at a baseline value and reaches a first voltage value a first period of time after receiving a post-synaptic spike at a second input, followed by a second voltage value a second period of time after the post synaptic spike, followed by a return to said baseline voltage a third period of time after the post-synaptic spike. The generated pre-synaptic pulse is applied to a pre-synaptic node of a synaptic device in series with a rectifying element that has a turn-on voltage based on a threshold. The generated post-synaptic pulse is applied to a post-synaptic node of said synaptic device.

Abstract: A method of information retrieval that includes determining Q generative models (?) in accordance with Probabilistic Latent Semantic Indexing (PLSI). The Q generative models are determined in offline training. The method also includes receiving a user query (q), choosing N generative models out of the Q generative models, and determining a content item (d) based on the query and a combination of the N generative models.

Abstract: Systems, methods, and apparatus are provided for determining relevance of documents to queries. An optimized relevance function is configured to determine a relevance value of documents of a first type that are linked to documents of a second type. The relevance function is optimized to satisfy certain criteria. According to one criterion, a relevance value produced by the optimized relevance function, when invoked for documents of the first type, should have a locally maximal degree of fit to the results of the existing relevance function for the sample training documents of the second type. An assessed degree of fit of a document can be increased or decreased to arrive at an optimized relevance function that ranks the documents of the first type in a desired position relative to documents of the second type in search results. The degree of fit can be assessed by a user-provided objective function.

Abstract: An apparatus includes an analytic network process (ANP) storage memory that stores an ANP weighted supermatrix representing an ANP model; and a processor in communication with the ANP storage memory. The processor is configured to facilitate measuring an instantaneous rate of change of alternative scores with respect to a fixed node of the ANP model, to determine a marginal influence of the fixed node. Also, the processor is configured to facilitate maintaining a same proportionality in the stored ANP weighted supermatrix as an importance of the fixed node is changed to measure the instantaneous rate of change.

Abstract: A computing device is described herein for detecting and addressing unintended contact of a hand portion (such as a palm) or other article with a computing device. The computing device uses multiple factors to determine whether input events are accidental, including, for instance, the tilt of a pen device as it approaches a display surface of the computing device. The computing device can also capture and analyze input events which represent a hand that is close to the display surface, but not making physical contact with the display surface. The computing device can execute one or more behaviors to counteract the effect of any inadvertent input actions that it may detect.

Abstract: A computing arrangement for identification of a current temporal input against one or more learned signals. The arrangement comprising a number of computational cores, each core comprises properties having at least some statistical independency from other of the computational, the properties being set independently of each other core, each core being able to independently produce an output indicating recognition of a previously learned signal, and at least one decision unit for receiving the produced outputs from the number of computational cores and making an identification of the current temporal input based the produced outputs.

Abstract: A “Cross-Lingual Unified Relevance Model” provides a feedback model that improves a machine-learned ranker for a language with few training resources, using feedback from a more complete ranker for a language that has more training resources. The model focuses on linguistically non-local queries, such as “world cup” (English language/U.S. market) and “copa mundial” (Spanish language/Mexican market), that have similar user intent in different languages and markets or regions, thus allowing the low-resource ranker to receive direct relevance feedback from the high-resource ranker. Among other things, the Cross-Lingual Unified Relevance Model differs from conventional relevancy-based techniques by incorporating both query- and document-level features.

Abstract: Certain embodiments of the present disclosure support techniques for simplified hardware implementation of the reward-modulated spike-timing-dependent plasticity (STDP) learning rule in networks of spiking neurons.

Abstract: Many computing scenarios involve the classification of content items within one or more categories. The content item set may be too large for humans to classify, but an automated classifier (e.g., an artificial neural network) may not be able to classify all content items with acceptable accuracy. Instead, the automated classifier may calculate a classification confidence while classifying respective content items. Content items having a low classification confidence may be sent to a human classifier, and may be added, along with the categories identified by the human classifier, to a training set. The automated classifier may then be retrained using the training set, thereby incrementally improving the classification confidence of the automated classifier while conserving the involvement of human classifiers. Additionally, human classifiers may be rewarded for classifying the content items, and the costs of such rewards may be considered while selecting content items for the training set.

Abstract: Methods and systems for controlling a prosthesis using a brain imager that images a localized portion of the brain are provided according to one embodiment of the invention. For example, the brain imager can provide motor cortex activation data using near infrared imaging techniques and EEG techniques among others. EEG and near infrared signals can be correlated with brain activity related to limbic control and may be provided to a neural network, for example, a fuzzy neural network that maps brain activity data to limbic control data. The limbic control data may then be used to control a prosthetic limb. Other embodiments of the invention include fiber optics that provide light to and receive light from the surface of the scalp through hair.

Abstract: User authentication apparatus controlling access to systems, inputs owner's login name and password and then extracts the owner's timing vectors from keystroke characteristics with which the owner forms a training set. A semantic network uses multiple links to indicate that different pattern components of user's behavioral access create different kinds of relationships and “symbolic representations”. A neural network is trained by using each of the owner's timing vectors in the training set as an input. When a user inputs the owner's login name and password, it's checked and the user's timing vector is extracted to type the user's password if checked and demoted in confidence level if otherwise. The user's timing vector is applied to neural network and difference between the input/output is compared with a predetermined threshold; and if the difference is greater than the threshold, is prohibited. Preferably this is aided by response time to personal questions.

Abstract: Systems and methods for automated document separation. The system includes a host device that is configured to communicate with one or more client devices over a network. The host device includes a splitting module, a correction module, a knowledge base, and a document store. The splitting module is configured to perform a multi-level document splitting. Pages are grouped into documents based on the sender information, the lack of sender information, and whether the sender is known. The splitting module performs an automatic correction of the initial document separation based on information stored within the knowledge base. The knowledge base is updated each time a document is processed and a user provides feedback related to whether the documents were successfully separated. Based on the success or failure of a particular document separation, the knowledge base evaluates the modifications made by a user to learn from the errors made during document separation.

Abstract: Seed candidate solutions can be inserted into the later generations of the population of an optimization problem during an evolutionary algorithm based simulation. Seed candidate solutions can be determined in response to an evolutionary algorithm based simulator receiving a problem description of an optimization problem. The seed candidate solutions can be sorted according to the seed candidate solutions' fitness. The simulator can start an evolutionary algorithm based simulation with a randomly generated initial population. The simulator can detect a condition for inserting seed candidate solutions into the population. The simulator can then insert the first seed candidate into the current population that is generated by the simulator in accordance with the evolutionary algorithm. A solution to the optimization problem can be determined based on successive generation of candidate solutions and insertion of additional seed candidate solutions in subsequent generations of the population.

Abstract: A method for the computer-assisted control and/or regulation of a technical system is provided. The method is used to efficiently reduce a high-dimensional state space describing the technical system to a smaller dimension. The reduction of the state space is performed using an artificial recurrent neuronal network. In addition, the reduction of the state space enables conventional learning methods, which are only designed for small dimensions of state spaces, to be applied to complex technical systems with an initially large state space, wherein the conventional learning methods are performed in the reduced state space. The method can be used with any technical system, especially gas turbines.