Abstract: Apparatus and methods for learning and training in neural network-based devices. In one implementation, the devices each comprise multiple spiking neurons, configured to process sensory input. In one approach, alternate heterosynaptic plasticity mechanisms are used to enhance learning and field diversity within the devices. The selection of alternate plasticity rules is based on recent post-synaptic activity of neighboring neurons. Apparatus and methods for simplifying training of the devices are also disclosed, including a computer-based application. A data representation of the neural network may be imaged and transferred to another computational environment, effectively copying the brain. Techniques and architectures for achieve this training, storing, and distributing these data representations are also disclosed.

Abstract: A system for automated contract management includes a computing device (102) and a memory storing program instructions that when executed by computing device (102). The program instructions cause the computing device (102) to generate an ontology (115) of terms and cross-contractual relationships in contracts (105, 110) and machine interpretable terms (120) and cross-contractual relationships (125) derived from the contracts (105, 110) with reference to the ontology (115). A method for automated contract management is also provided.

Abstract: Embodiments of the present invention relate to a method and system for automatic event analysis. In particular, according to embodiments of the present invention, there is disclosed a method for automatic event analysis, comprising: collecting information on events of a predetermined type occurring at, within a period of time, at least one location in a space; determining a predictability of the events of the predetermined type with respect to the at least one location based on the collected information and a predetermined condition(s) related to the events of the predetermined type; and determining the stability of predictable events with respect to the at least one location within the period of time. Further, there is disclosed a corresponding system. According to embodiments of the present invention, it is possible to classify an event associated with a service and analyze the service demands in a more efficient way.

Abstract: A method for matching an advertisement item to a multimedia content element. The method comprises extracting at least one multimedia content element from a web-page requested for display on a user node; generating a signature of the at least one multimedia content element; searching for at least one advertisement item respective of the signature; and causing the display of the at least one advertisement item within a display area of the web-page.

Abstract: The present disclosure includes systems and methods for detecting an anomaly in crowd behavior. The method includes receiving sensor data representing a crowd, and partitioning the sensor data into local areas forming neighborhoods. The method further includes, for each local area, characterizing motion in the local area to determine real-time estimates of motion of sub-populations based on the sensor data, providing a crowd model for each local area, representing continuous functions describing expected motion near each local area, and determining parametric values of the crowd model based on the real-time estimates of the motion of the sub-populations.

Abstract: Apparatus and methods for plasticity in a spiking neuron network. In one implementation, a plasticity mechanism is configured based on a similarity measure between neuron post-synaptic and pre-synaptic activity. The similarity measure may comprise a cross-correlogram between the output spike train and input spike train, determined over a plasticity window. Several correlograms, corresponding to individual input connections delivering pre-synaptic input, may be combined. The combination may comprise for example a weighted average. The averaged correlograms may be used to construct the long term potentiation component of the plasticity. The long term depression component of the plasticity may comprise e.g., a monotonic function based on a statistical parameter associated with the adaptively determined long term potentiation component.

Abstract: Apparatus and method for assessing odors, comprises an electronic nose, to be applied to an odor and to output a structure identifying the odor; a neural network which maps an extracted structure to a first location on a pre-learned axis of odor pleasantness; and an output for outputting an assessment of an applied odor based on said first location. The assessment may be a prediction of how pleasant a user will consider the odor.

Abstract: A method of classifying information in an optical analysis system includes obtaining calibration data defining a plurality of data points, each data point representing values for two or more detectors when sampling a material used to construct a multivariate optical element. Based on the calibration data, one or more validation models can be developed to indicate one or more ranges of expected results. Validation data comprising the models can be used to compare data points representing values for two or more detectors when performing a measurement of a material to determine if the data points fall within an expected range. Classification data can be generated based on the comparison and, in some embodiments, one or more indicators, such as a confidence level in a measurement, can be provided.

Abstract: A method of labeling an unlabeled message of a social stream. The method including training a training model based on labeled messages, partitioning the training model into a plurality of class partitions, each comprising statistical information and a class label, computing a confidence for each of the class partitions based on information of an unlabeled message and the statistical information of a respective class partition, as executed by a processor in a computer system, and labeling the unlabeled message of the social stream according to respective confidences of the class partitions.

Abstract: A computer-implemented adaptive experimentation method and system is described that automatically selects and executes information gathering actions. The adaptive experimentation method and system integrates value of information considerations, experimental design, and inferences from experimental results. The experimental results may include behaviors of users of a computer-based system. The process enables an automatic, adaptive process for attaining additional information and applying the attained information in making subsequent experiment decisions.

Abstract: Embodiments of the present application relate to a personalized information pushing method, a personalized information pushing device, and a computer program product for pushing personalized information. A personalized information pushing method is provided. The method includes retrieving network behavior data related to access operations performed by user terminals, determining a numerical value of a degree of correlation between a user terminal and a plurality of information providing terminals having a correlation within a set time window based on the network behavior data, retrieving information providing terminals corresponding to a first user terminal to form a first data set based on the numerical values, retrieving information of the information providing terminals from the first data set to generate a first information, and pushing the first information to the first user terminal.

Abstract: A system for developing and implementing empirically derived algorithms to generate decision rules to predict invalidity of subject reported data and fraud with research protocols in surveys allows for the identification of complex patterns of variables that detect or predict subject invalidity of subject reported data and fraud with the research protocol in the survey. The present invention may also be used to monitor invalidity of subject reported data within a research protocol to determine preferred actions to be performed. Optionally, the invention may provide a spectrum of invalidity, from minor invalidity needing only corrective feedback, to significant invalidity requiring subject removal from the survey. The algorithms and decision rules can also be domain-specific, such as detecting invalidity or fraud among subjects in a workplace satisfaction survey, or demographically specific, such as taking into account gender or age.

Abstract: Values of a variable affecting the determination of the driver of a shared ride may be calculated. Each value may be associated with a respective potential driver. An optimal value from the calculated values may be selected. A potential driver associated with the selected optimal value may be assigned as the driver of the shared ride. The variable may be carbon emission, electricity consumption, passenger to driver role ratio, driving distance, driving time, vehicle size, fuel efficiency, electricity to gasoline usage ratio, accident occurrence, vehicle safety, vehicle comfort, or vehicle speed. The optimal value may be the lowest value or the highest value from the calculated values. Each value may be calculated based on parameters specified by the respective potential driver.

Abstract: An intelligent control system based on an explicit model of cognitive development (Table 1) performs high-level functions. It comprises up to O hierarchically stacked neural networks, Nm, . . . , Nm+(O?1), where m denotes the stage/order tasks performed in the first neural network, Nm, and O denotes the highest stage/order tasks performed in the highest-level neural network. The type of processing actions performed in a network, Nm, corresponds to the complexity for stage/order m. Thus N1 performs tasks at the level corresponding to stage/order 1. N5 processes information at the level corresponding to stage/order 5. Stacked neural networks begin and end at any stage/order, but information must be processed by each stage in ascending order sequence. Stages/orders cannot be skipped. Each neural network in a stack may use different architectures, interconnections, algorithms, and training methods, depending on the stage/order of the neural network and the type of intelligent control system implemented.

Abstract: A system and method of processing one or more sensor logs includes receiving a sensor log an identifying a set of entries in the sensor log having a predefined sequence of sensor identifiers. The set of entries may define a velocity event. The method can also provide for calculating an in-home gait velocity for the velocity event. In one example, the method also provides for identifying another set of entries in the sensor log having a sensor identifier that corresponds to a dwell sensor mounted in a doorway, wherein the other set of entries define a dwell event. The method may also provide for calculating an in-home dwell time for the dwell event.

Abstract: According to a method for creating a model for a travel time database, a leg network comprising leg sections between a starting point and a destination point are analyzed. Multiple routes are ascertained between the starting and destination points. Each leg section of a route is associated with a relative travel time loss and is weighted. The ascertained travel time losses and the associated weightings are used as input data for a learning method by way of which an existing knowledge base is iteratively expanded.

Abstract: A system and computer-implemented method for determining a threat level for one or more individuals includes accessing a data structure to obtain aggregated data stored therein, wherein the aggregated data comprises at least one of communication history data or transaction history data for one or more individuals. One or more predetermined metrics are applied to the obtained aggregated data, to determine threat level information for the one or more individuals. The determined threat level information is provided for display.

Abstract: Embodiments of the invention provide techniques for processing abstract rules with limiting criteria. In one embodiment, limiting criteria may specify requirements for characteristics of sets of input or output values of processing abstract rules. For example, limiting criteria may specify requirements for statistical validity of a set of input values, such as a minimum record count. In one aspect, limiting criteria may include input criteria applied to input data prior to being processed in a rule engine. In another aspect, limiting criteria may include output criteria applied to an output of a rule engine. In the event that limiting criteria are not satisfied, the processing of the abstract rule may be terminated.

Abstract: Described is a system and method for determining a classification of an application that includes initiating a stress test on the application, the stress test including a predetermined number of stress events, wherein the stress events are based on a network impairment. A response by the application to each stress event is identified and the application is classified as a function of the response into one of a first classification and a second classification, the first classification indicative of a normal application and the second classification indicative of an undesired application. If, the application is in the second classification, a network response procedure is executed.

Abstract: The present invention generally relates to utilization of at least two known location addresses yielding accurate determination of a user's mode of operations and/or preferences. In one embodiment, the present invention utilizes proximity and/or vector between a current location address and a known home or work address to determine preferences that dynamically change based on the current location and inter-relationship between the current location and at least one other known location address.