Abstract: A method for providing a personalized health risk of a patient includes receiving training data corresponding to a plurality of patients and target data corresponding to a target patient; generating model data based on the training data according to an anomaly detection method; either determining whether the target data is anomalous with respect to the training data, or determining the extent to which the target data is anomalous with respect to the training data; and either indicating whether the target patient is at risk of the adverse outcome, or indicating the extent to which the target patient is at risk of the adverse outcome.

Abstract: A neuromorphic data processing device comprising a plurality of spiking neurons, with each of these neurons comprising: an integrator designed to receive successive analog pulses each having a certain value, and accumulate the values of the pulses received in a recorded value, referred to as accumulation value, and a discharger designed to emit a pulse, referred to as discharge pulse, according to the accumulation value, and a silicon support having two surfaces, the neurons being carried out on at least one of the two surfaces, the integrator of each neuron comprising a metal via of the TSV type between the two surfaces of the silicon support, the metal via of the TSV type forming a capacitor with the silicon support and having an electric potential forming the accumulation value wherein the values of the pulses received are accumulated and according to which the discharge pulse is emitted.

Abstract: Methods and apparatus for suggesting image, video, and image album titles are presented. A machine-learning service executing on a mobile platform receives feature-related data. The feature-related data includes image-related data related to one or more images received from an application executing on the mobile platform and platform-related data received from the mobile platform. The image-related data and the platform-related data differ. The machine-learning service generates a title related to the one or more images by performing a machine-learning operation on the feature-related data. The machine-learning service sends the title related to the one or more images to the application.

Abstract: An email activity pattern of a user is analyzed. A time probability for the user to act on an email sent to the user is determined based upon, at least in part, the email activity pattern of the user.

Abstract: The learning method taught in this patent document is significantly different from previous methods for automatic classification of citations that are labor intensive and subject to human bias and error. The present invention automatically generates and avoids these limitations. A set of operational definitions and features uniquely suited to the scientific literature is disclosed along with their use with a learning method that is capable of analyzing the textual content of articles along with bibliometric data to accurately classify instrumental citations.

Abstract: A method for a system that indexes, ranks, and clusters multimedia documents using organizing means, scoring means, and stochastic means that optimizes parameter sets comprising of object parameters. The method creates a plurality of individual parameter sets, the parameter sets comprising information sharing system object parameters for describing a structures, search query sets, and dynamic search spaces to be optimized and setting the population of individuals as a population of memes. These parameters are required to filter, organize, and index any large-scale data set—information stored on a single computer, a local area network (LAN), and a wide area network (WAN) that encompasses the whole Internet—that may consists of constantly fluctuating information content over relatively short periods of time.

Abstract: A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.

Abstract: Nearly orthogonal latin hypercubes are used in optimization algorithms for creating an expanded and synthetically-generated data set to improve an initial optimization algorithm.

Abstract: Methods and systems for predicting statistically probable systematically assigned identifiers are disclosed, as are methods and systems for determining the likelihood that a systematically assigned identifier provided by a purported assignee of the identifier is legitimate. In one example, determining the likelihood of legitimacy includes determining the likelihood that the provided identifier is a valid identifier and determining the likelihood that the provided identifier was assigned to the purported assignee. To accomplish this validation, the present disclosure employs patterns of assignment discernable for systematically assigned identifiers in combination with statistical methods.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for location centric user profiling and services. In one aspect, a method includes accessing historical location data specifying physical locations at which user devices were detected; accessing network data for each of the users of the user devices, the network data for each user indicative of subjective preferences of the user; for each of the users, determining physical locations specified by the location data, determining entities from the physical locations and visited by the user, determining for each entity a satisfaction measure that is indicative of a satisfaction of the user with the entity, and generating a user profile for the user specifying topics that are of interest to the user, the entities having been determined to have been visited by the user, and the satisfaction measures of the entities.

Abstract: A rule packaging system and method to define and/or package parameters, attributes, enumerations of a prime rule in a reduced canonical form suitable for propositional logic manipulation using, for example, zero-suppressed binary decision diagrams. The reduced form of the prime rule is subsequently used by applying a series of user inputs to determine a result that preferably includes conflict and selection advice to guide the user to satisfaction. Elective events, such as but not limited to the display of messages or the performance of calculations, may optionally be packaged along with the prime rule or components thereof, and presented during execution to help guide an end user to satisfaction or compliancy when choosing among possible configuration parameters. The apparatus automates determination of a complex rule having a combinatorial exploded number of rule components, or a combinatorial number of possible outcomes, exceeding computational capacity of present day computing systems.

Abstract: Autonomous biologically based learning tool system(s) and method(s) that the tool system(s) employs for learning and analysis of performance degradation and mismatch are provided. The autonomous biologically based learning tool system includes (a) one or more tool systems that perform a set of specific tasks or processes and generate assets and data related to the assets that characterize the various processes and associated tool performance; (b) an interaction manager that receives and formats the data, and (c) an autonomous learning system based on biological principles of learning. Objectively generated knowledge gleaned from synthetic or production data can be utilized to determine a mathematical relationship among a specific output variable and a set of associated influencing variables. The generated relationship facilitates assessment of performance degradation of a set of tools, and performance mismatch among tools therein.

Abstract: Systems, methods and computer program products for classifying documents are presented. Systems, methods and computer program products for analyzing documents, e.g., associated with legal discovery are also presented. Systems, methods and computer program products for cleaning up data are also presented. Systems, methods and computer program products for verifying an association of an invoice with an entity are also presented. Systems, methods and computer program products for managing medical records are presented. Systems, methods and computer program products for face recognition are presented.

Abstract: In the present invention, a data processing device for processing streams of network borne data includes content inspection logic configurable to perform pattern matching functions on a received content stream and output match data, and a microengine for executing computer coded instructions, the microengine being coupled to the content inspection logic for configuring the pattern matching function of the content inspection unit in respect of a particular processing job for the received content stream and for processing the content stream independence on the match data. The microengine is adapted to reconfigure dynamically the content inspection logic in dependence on the match data thereby to modify the pattern matching function performed by the content inspection logic on the content stream during the course of a processing job. The present invention provides a novel architecture and method for processing content as it flows through a network.

Abstract: A method for automatic, or semi-automatic, planning of dental treatment for a patient comprises: (a) obtaining data about an area which is to be treated and data about a face of a patient; (b) performing a computer-assisted analysis of the data to determine properties of at least the face of the patient; (c) creating a modified tooth set-up using a set of stored rules which make use of the determined facial properties. A three-dimensional representation simulates the appearance of the modified tooth set-up and the patient's face surrounding the treatment area. The method also determines properties of existing teeth and creates a modified tooth set-up which is also based on the existing teeth of the patient. The method can be implemented as software running on a workstation.

Abstract: A method of determining whether a sprite will be generated determines a probability of a first page module being displayed on a web page together with a second page module, and if the probability exceeds a predetermined threshold, generates the sprite based on a first image within the first page module and a second image within the second page module, a rule indicating that the sprite contains the first image and the second image, and a style sheet code associated with the sprite.

Abstract: A modeling method of neuro-fuzzy system including a rule-defining process and a network-building process is disclosed. The rule-defining process divides a plurality of training data into a plurality of groups to accordingly define a plurality of fuzzy rules, and the network-building process constructs a fuzzy neural network based on the fuzzy rules obtained by the rule-defining process. The provided modeling method of neuro-fuzzy system is capable of building a neuro-fuzzy system extremely similar to an original function that generates training data of the neuro-fuzzy system.

Abstract: A method and apparatus for providing an adaptive parser are disclosed. For example, the method receives a configuration for a router, and parses a command from the configuration. The method determines whether there is an existing entry for the command in a model of a configuration language, wherein the model of the configuration language is used to record a syntactic structure of each command in the configuration language and its relationship to other commands. The method creates a new entry for the command in the model of the configuration language, if there is no existing entry for the command; and uses the model to update the parser.

Abstract: Methods, systems and articles of manufacture for identifying semantic nearest neighbors in a feature space are described herein. A method embodiment includes generating an affinity matrix for objects in a given feature space, wherein the affinity matrix identifies the semantic similarity between each pair of objects in the feature space, training a multi-bit hash function using a greedy algorithm that increases the Hamming distance between dissimilar objects in the feature space while minimizing the Hamming distance between similar objects, and identifying semantic nearest neighbors for an object in a second feature space using the multi-bit hash function. A system embodiment includes a hash generator configured to generate the affinity matrix and train the multi-bit hash function, and a similarity determiner configured to identify semantic nearest neighbors for an object in a second feature space using the multi-bit hash function.

Abstract: A missing case of a fixed scope can be detected among a plurality of business rules of unrestricted forms. According to one or more embodiments, the described detecting includes building a rules inhibition graph for the plurality of business rules representing a constraint model comprising a plurality of nodes and describing a plurality of cases which make the plurality of business rules non-applicable; labeling the rules inhibition graph with values satisfying constraints of the constraint model by search and inference, and determining a missing case when a consistent labeling satisfying the constraints of the constraint model is obtained. Using one or more of the described embodiments missing cases which may result from unforeseen interactions of overlapping tests over an a priori unknown number of attributes among arbitrary business rules may be detected.