Abstract: Various amounts of information can be beneficial to different controllers configured upon an industrial control system. Information can be retained in a distributed directory such that controllers quickly learn information concerning other controllers. The distributed directory can be automatically constructed and populated with information from different controllers. When a module enters an industrial control system, information can automatically advertise to other units through use of the distributed directory.

Abstract: A special purpose processor (SPP) for implementing a synthetic neural model of the biological anatomy of the human brain to control a brain-based device (BBD) that is movable in a real-world environment, including neural processing units (NPUs), each having a programmed processor and a local memory that stores data records of neural elements, a system memory for storing data about all the NPUs, and a finite state machine and a system bus for transferring data between the NPUs and system memory.

Abstract: Boosting algorithms are provided for accelerated machine learning in the presence of misclassification noise. In an exemplary embodiment, a machine learning method having multiple learning stages is provided. Each learning stage may include partitioning examples into bins, choosing a base classifier for each bin, and assigning an example to a bin by counting the number of positive predictions previously made by the base classifier associated with the bin.

Abstract: In one aspect, the invention is based on a process that combines information present in a joint distribution of the predictor variables and the variable (or variables) to be predicted. This information may be captured in the form of a table or other like data structure that includes a set of vectors (referred to as a “TAB”). The process uses the information in the TAB in conjunction with one or more rules. In one embodiment, a set of different rules are applied to the TAB to determine which rule in the set produces the most accurate predictions. The RULE that produces the most accurate predictions is then used in conjunction with observed information to make predictions.

Abstract: A computer-implemented method is provided for determining a corrective action. The method may include obtaining diagnostic data and calculating, using the diagnostic data, a prognostic. The method may also include retrieving, when the prognostic is above an alarm level, historical records and calculating a Bayesian posterior probability using the diagnostic data and the historical records. Further, the method may include calculating a prognostic prescience metric using the diagnostic data and the historical records and determining, based on the Bayesian posterior probability, the prognostic prescience metric, and an economic calculation, the corrective action.

Abstract: A system and method for processing information in unstructured or structured form, comprising a computer running in a distributed network with one or more data agents. Associations of natural language artifacts may be learned from natural language artifacts in unstructured data sources, and semantic and syntactic relationships may be learned in structured data sources, using grouping based on a criteria of shared features that are dynamically determined without the use of a priori classifications, by employing conditional probability constraints.

Abstract: A system and method to facilitate inventory forecasting of network traffic for a network-based entity are described. In one example, the method includes preprocessing historical data to obtain processed average data, applying modeling and forecasting techniques to the processed average data using a seasonal auto-regressive integrated moving average process to obtain forecasting results, and combining the forecasting results to output combined forecasting data, wherein the combining the forecasting results comprises receiving and storing yearly forecast results. In one implementation, the historical data is normalized by weekly average to obtain normalized data. In another implementation, trend and seasonality are removed from a set of processed data to obtain stationary data. In yet another implementation, yearly forecast results are received and stored.

Abstract: Embodiments of prime indexing and/or other related operations are disclosed. prime indexing and/or other related operations are disclosed.

Abstract: A method for scheduling and usage of bandwidth wherein data is transmitted to an artificial intelligence model for analysis and assigned a ranking. An event resource allocation model analyzes the ranking and determines how to compress the associated video. The event resource allocation model also determines when to compress the remotely stored video and transmit to a central data center where the video may be reviewed.

Abstract: A multiprocessor system which includes automatic workload distribution. As threads execute in the multiprocessor system, an operating system or hypervisor continuously learns the execution characteristics of the threads and saves the information in thread-specific control blocks. The execution characteristics are used to generate thread performance data. As the thread executes, the operating system continuously uses the performance data to steer the thread to a core that will execute the workload most efficiently.

Abstract: An intelligent distributed computing fabric system may comprise a cognitive element, a computing element, a security element, and a network element. The cognitive element may receive inputs from the computing element, the security element, and the network element, and may further receive external information from a sensor interface. The cognitive element may process the inputs from the computing element, the security element, and the network element, and may additionally process the external information from the sensor interface. The cognitive element may make decisions based on the inputs from the computing element, the security element, and the network element, and based on the external information from the sensor interface, to adapt for dynamically varying situations in a fabric infrastructure.

Abstract: A method is provided for operating a computing device to create a document structure model of a computer parsable text document utilizing recognition of at least one ordered sequence of identifiers in the document. The method includes converting a computer parsable text document of any format to an alternative structured language format to form a converted document. The text of the converted document is fragmented into an ordered sequence of text fragments within a text format. The text fragments are enumerated to obtain a sequence of terms. At least one optimal sub-sequence of terms is identified from among the sequence of terms, with an optimal sub-sequence being one or more longest increasing sub-sequence(s). The computer parsable text document is annotated with tags, with the tags including information derived from identification of the optimal sub-sequence(s). The annotated document is displayed on the graphical user interface.

Abstract: A sensor manager comprising: a situation information expected value network and an information instantiator. The situation information expected value network includes a probabilistic network configured to generate situation probabilities using situation data; and an expected information gain determination module configured to generate an information request using expected changes in the situation probabilities. The information instantiator is configured to generate a sensor observation request utilizing the information request and the situation data. The situation data includes at least one of the following: a goal lattice structure data; a goal lattice value; a kinematic state estimate; a non-kinematic state estimate; a search probability mass function; a sensor applicable function table; or any combination of the above. The probabilistic network includes: at least one managed evidence node; at least one unmanaged evidence node; and at least one situation evidence node.

Abstract: Disclosed are embodiments of systems and methods for prioritizing mobile media player files by providing for the automated addition and/or deletion of media items for a mobile media player. In some embodiments, a statistical method may be provided for inferring which media items on a mobile media player should be deleted based on, for example, user taste data. In some embodiments, new media items may be loaded onto a user's mobile media player by creating one or more playlists from a playlist builder. The playlist(s) may be created by using user taste data. Rankings may also be created to determine an order for deletion of the media items currently on a mobile media player and/or for addition of new media items to the device.

Abstract: Aspects of the subject matter described herein relate to predicting and using search engine switching behavior. In aspects, switching components receive a representation of user interactions with at least one browser. The switching components derive information from the representation that is useful in predicting whether a user will switch search engines. The derived information and information about a user's current interaction with a browser is then used by a switch predictor to predict whether the user will switch search engines. This prediction may be used in a variety of ways examples of which are given herein.

Abstract: Aggregate scoring is used to help classify digital content such as content uploaded to multi-user websites (e.g., social networking websites). In one embodiment, specific categories are used that relate to a social implication of content. For example, text, images, audio or other data formats can provide communication perceived to fall into categories such as violent, abusive, rights management, pornographic or other types of communication. The categories are used to provide a raw score to items in various groupings of a site's content. Where items are related to other items such as by organizational, social, legal, data-driven, design methods, or by other principles or definitions, the related items' raw scores are aggregated to achieve a score for a particular grouping of items that reflects, at least in part, scores from two or more of the related items.

Abstract: A technique is provided to coarse-class one or more customer characteristics used in a predictive model. A set of functions are used to represent partition points of the customer characteristic into smaller classes. Each of the final classes of the customer characteristic is represented separately in the predictive model. An initial set of functions may be established to provide an initial set of partitions points of the customer characteristic. The set of functions is then processed using a genetic algorithm to evolve the partition points to new values. Processing the set of partitions using the genetic algorithm may continue until a stopping criterion is reached.

Abstract: A system for information searching includes a first layer and a second layer. The first layer includes a first plurality of neurons each associated with a word and with a first set of dynamic connections to at least some of the first plurality of neurons. The second layer include a second plurality of neurons each associated with a document and with a second set of dynamic connections to at least some of the first plurality of neurons. The first set of dynamic connections and the second set of dynamic connections can be configured such that a query of at least one neuron of the first plurality of neurons excites at least one neuron of the second plurality of neurons. The excited at least one neuron of the second plurality of neurons can be contextually related to the queried at least one neuron of the first plurality of neurons.

Abstract: Character string divider divides a targeted character string into a plurality of groups at each bonding sites on a main chain. In the character string dividing process, the character string divider adds starting/ending symbols to the targeted character string, inserts a delimiter between adjacent characters, changes a notation related to oxo acids, reconstructs an atomic symbol consisting of two characters, changes a notation regarding a subscript or superscript, links hydrogen to another element, reconstructs a set of side chains, reconstructs a character string consisting of one group, reconstructs a back-end group, reconstructs a double bond in a group, and removes the starting/ending symbols. Character string reverser reverses the alignment of the groups.

Abstract: Described herein is technology for, among other things, enabling use of custom expressions in a rules engine. The rules engine may be used in conjunction with a workflow. The technology involves providing a custom expression with access to validation context and execution context of the workflow. The custom expression can then participate in rules engine validation and execution. Furthermore, the technology allows for variables of the custom expression to be analyzed so that the rules engine can discover the variable dependencies of the custom expression and any side effects that drive forward chaining.