Abstract: Exemplary methods and apparatuses are provided which may be used for classifying and indexing segmented portions of web pages and providing related information for use in information extraction and/or information retrieval systems. In an embodiment, an index of segmented portions may be used by a search engine to respond to a search query. In an embodiment, one or more machine learned models may be used to identify one or more feature properties of a plurality of segmented portions within one or more files, or otherwise inferable from the one or more files. In an embodiment, one or more machine learned models may be used to classify one or more of a plurality of segmented portions as being at least one of a plurality of segment types.

Abstract: Disclosed is a vehicular environment estimation device capable of accurately estimating a travel environment around own vehicle on the basis of a predicted route of a mobile object or the like, which is moving in a blind area. A vehicular environment estimation device that is mounted in the own vehicle detects a behavior of another vehicle in the vicinity of the own vehicle, and estimates a travel environment, which affects the traveling of another vehicle, on the basis of the behavior of another vehicle. For example, the presence of another vehicle, which is traveling in a blind area, is estimated on the basis of the behavior of another vehicle. Therefore, it is possible to estimate a vehicle travel environment that cannot be recognized by the own vehicle but can be recognized by another vehicle in the vicinity of the own vehicle.

Abstract: Building a runtime dialog is provided. An initial answer to an initial question is received from a user. A state of a conversation thread is created based on the initial answer. A next question to ask is automatically selected by a processor based on the updated state of the conversation thread. The next question is presented to the user. A next answer to the next question is received. The state of the conversation thread is updated based on the next answer. The selecting, presenting, receiving, and updating are repeated until a criterion is satisfied.

Abstract: A physical environment is equipped with a plurality of non-obtrusive sensors (e.g., motion sensors). As a plurality of residents perform various activities within the physical environment, sensor readings are received from one or more of the sensors. Based on the sensor readings, each of the plurality of residents is identified and locations of each of the plurality of residents are tracked.

Abstract: A model-based control system for controlling a production system is disclosed. The production system provides jobs and objectives to the model-based control system. The model-based control system includes, a planner operative to provide the production system with a plan, the planner generating the plan using a depth-first target value search. The depth-first target value search being configured to generate the plan with a failure probability most closely approximating a target value. Also provided is a system model operative to model the behavior of the production system. Another aspect of the model-based control system is a diagnosis engine operative to estimate failure probabilities for plans and provide diagnostic guidance to the planner. The model-based control system including the planner, the system model and diagnosis engine are implemented via a digital processing device.

Abstract: Described is a system, method, and computer program product for feature detection with spiking dynamics. The system is configured to perform operations of first receiving an input pattern comprising a plurality of features. The input pattern is then translated into a spike-coded representation of the input pattern. The spike-coded representation of the input pattern is transferred to a feature detector layer of a feature detector network comprising a set of feature detector neurons having input weights. Each feature detector neuron in the set of feature detector neurons then competes for the feature detector neuron whose input weights best represent the input pattern. Finally, the input weights which compressively code frequently seen input patterns are updated according to a set of learning rules. Also presented is a novel set of rules that transform the functional properties of rate-coded models into the spiking domain.

Abstract: An anomalous effect detector responsive to an influence of mind comprises a source of non-deterministic random numbers, SNDRN, a phase-sensitive filter and a results interface. In some embodiments, the phase-sensitive filter comprises a complex filter. An artificial sensory neuron comprises a SNDRN. Preferably, several artificial sensory neurons are grouped in a small volume. An analog artificial sensory detector comprises a plurality of analog artificial sensory neurons, an abstracting processor and a control or feedback unit. Some embodiments include an artificial neural network. An artificial consciousness network contains a plurality of artificial neural networks. One of the artificial neural networks comprises an activation pattern meta-analyzer. An artificial consciousness device comprises a cluster of artificial consciousness networks, a sensory input device to provide sensory input signals to the input of one or more ANNs in ACD, and an output device.

Abstract: Methods and systems are provided that may be utilized to rank related news predictions and to provide one or more predictions to a user. In a particular implementation, one or more digital signals representing a query may be generated at least partially in response to an article being accessed by a user. One or more digital signals representing one or more predictions comprising one or more sentence portions having one or more references to one or more future dates may be obtained based at least in part on a comparison of the one or more digital signals representing the query with one or more digital signals representing a prediction index.

Abstract: The present invention relates to a system for deep packet inspection and intrusion detection. The system uses a pattern matching module receiving as an input a data stream in a neural network. Neurons are activated such that when active, the neuron fires to all connecting output neurons to form a neuron spike, each neuron spike from the assigned neuron to a connecting output neuron having a delay. A delay is associated with each input character in the pattern, such that a position of each input character relative to an end of the pattern is stored in an alphabet-pattern-delay matrix (APDFM). An activation matrix (AM) is used to match each input character with a stored pattern to generate a similarity match and determine if the string of characters is the stored pattern.

Abstract: Methods and arrangements for conducting a search using query logs. A query log is consulted and query rewrite rules are learned automatically based on data in the query log. The learning includes obtaining click-through data present in the query log.

Abstract: Electronic data interchange (EDI) documents are validated by creating an inventory of all rules, dynamically adjusting the inventory based upon entity specific rules derived from a plurality of companion guides, determining a profile containing pointers to select rules in the inventory for each companion guide and storing the profile for each companion guide in a storage. A runtime checker can then be used to check a received EDI document with a corresponding rule set, forward the EDI document if the EDI document matches its current rule set and return the EDI document if the EDI document does not match its current rule set. EDI rules may be enforced, for example, by determining entity-specific rules from corresponding companion guides, by expressing each rule in a neutral and machine readable format, by classifying the rules and/or by creating an inventory of rules and pointers to entity-specific rules.

Abstract: Activity templates are generated from one or more existing smart environments (e.g., source spaces) based on sensor data from the one or more existing smart environments that corresponds to known activities. A target activity template is then generated for a new smart environment, e.g., the target space. The source space activity templates are then mapped to the target activity templates to enable recognition of activities based on sensor data received from the target space.

Abstract: A “Contact Discriminator” provides various techniques for differentiating between valid and invalid contacts received from any input methodology by one or more touch-sensitive surfaces of a touch-sensitive computing device. Examples of contacts include single, sequential, concurrent, or simultaneous user finger touches (including gesture type touches), pen or stylus touches or inputs, hover-type inputs, or any combination thereof. The Contact Discriminator then acts on valid contacts (i.e., contacts intended as inputs) while rejecting or ignoring invalid contacts or inputs. Advantageously, the Contact Discriminator is further capable of disabling or ignoring regions of input surfaces, such tablet touch screens, that are expected to receive unintentional contacts, or intentional contacts not intended as inputs, for device or application control purposes.

Abstract: Embodiments of the invention relate to a time-division multiplexed neurosynaptic module with implicit memory addressing for implementing a neural network. One embodiment comprises maintaining neuron attributes for multiple neurons and maintaining incoming firing events for different time steps. For each time step, incoming firing events for said time step are integrated in a time-division multiplexing manner. Incoming firing events are integrated based on the neuron attributes maintained. For each time step, the neuron attributes maintained are updated in parallel based on the integrated incoming firing events for said time step.

Abstract: A mobile device, including an accelerometer and a processing unit receiving signals from the accelerometer and determining motion information of the mobile device based on the received signals is disclosed. A content selector selects a media format for content based on the physical state of the mobile device as indicated by the signals from the accelerometer. A display device displays the content in the selected media format. When the motion is a predetermined type of motion, the received content is withheld from being displayed by the display device. A machine learning apparatus is provided as the content selector.

Abstract: A method, a system and a computer program product for selecting a further inquiry for a user to clarify a request for information from the user. One or more candidate answers to the request for information from the user are determined, and a score value is generated for each of one or more characteristics of each candidate answer, where at least one characteristic is associated with an inquiry for the user to clarify the request for information. A characteristic associated with an inquiry is determined that includes score values providing the greatest potential adjustment for the candidate answers in response to a clarification of the request for information, and the inquiry is selected that is associated with the determined characteristic for presentation to the user.

Abstract: Several aspects for providing historical information to an event based image include a method, an apparatus and an article. One or more of the aspects includes receiving a trigger associated with a rule, determining if the rule requires that historical information be provided to an event-based analysis engine, filtering out events not needed by the rule if the rule requires historical information and providing the event-based analysis engine with historical information based on the filtering.

Abstract: Described is a technology for measuring the similarity between two objects (e.g., documents), via a framework that learns the term-weighting function from training data, e.g., labeled pairs of objects, to develop a learned model. A learning procedure tunes the model parameters by minimizing a defined loss function of the similarity score. Also described is using the learning procedure and learned model to detect near duplicate documents.

Abstract: A reasoning system is configured to interact with data processing elements of an information processing system. The reasoning system includes a reasoning module configured to perform one or more reasoning operations on metadata. The metadata characterizes data sets associated with the data processing elements in order to identify at least selected portions of one or more of the data sets as being suitable for use in achieving a designated purpose. The reasoning system also includes a dynamic information assembly module configured to utilize results of the one or more reasoning operations to assemble at least a subset of the selected portions so as to achieve the designated purpose. The reasoning system and associated data processing elements may be implemented, by way of example, in cloud infrastructure of a cloud service provider, or on another type of processing platform.

Abstract: A method, computer program product and computer system for predicting that an event identified in an event topic map meta-model will have an effect on at least one asset identified in an asset topic map meta-model. In an exemplary embodiment, a computer receives a query input from a user. The computer obtains an input of an event from the query input. The computer identifies at least one asset mapped to the event in an asset to event topic map meta-model that maps assets in the asset topic map meta-model to events in the event topic map meta-model. In identifying the at least one asset, the computer determines that the at least one asset has greater than a threshold probability of being affected by the event.