Abstract: An initial data analytic plan for analyzing a given data set associated with a given data problem is defined. At least a portion of original data in the given data set is conditioned to generate conditioned data. At least one model is selected to analyze at least one of the original data and the conditioned data. The at least one selected model is executed on at least one of a portion of the original data and a portion of the conditioned data. Results of the model execution are communicated to at least one entity, the results comprising a refined data analytic plan for analyzing the given data set. One or more computing resources are provisioned to implement the refined data analytic plan. The defining, conditioning, selecting, executing, communicating and provisioning steps are performed on one or more processing elements associated with a computing system and automate a data analytics lifecycle.

Abstract: A method of managing an axiom includes determining if an H in an A?H axiom in existing axioms is a predetermined expression; and if the H is the predetermined expression, collecting, from the existing axioms, a B?I axiom in which the B includes the H, deleting the A?H axiom from the existing axioms, and generating a new B?I axiom from the collected B?I axiom by replacing the H in the B with the A.

Abstract: Method, computer program product, and system to perform an operation for a deep question answering system. The operation begins by computing a concept score for a first concept in a first case received by the deep question answering system, the concept score being based on a machine learning concept model for the first concept. The operation then excludes the first concept from consideration when analyzing a candidate answer and an item of supporting evidence to generate a response to the first case upon determining that the concept score does not exceed a predefined concept minimum weight threshold. The operation then increases a weight applied to the first concept when analyzing the candidate answer and the item of supporting evidence to generate the response to the first case when the concept score exceeds a predefined maximum weight threshold.

Abstract: Method, computer program product, and system to perform an operation for a deep question answering system. The operation begins by computing a concept score for a first concept in a first case received by the deep question answering system, the concept score being based on a machine learning concept model for the first concept. The operation then excludes the first concept from consideration when analyzing a candidate answer and an item of supporting evidence to generate a response to the first case upon determining that the concept score does not exceed a predefined concept minimum weight threshold. The operation then increases a weight applied to the first concept when analyzing the candidate answer and the item of supporting evidence to generate the response to the first case when the concept score exceeds a predefined maximum weight threshold.

Abstract: Certain aspects of the present disclosure provide methods and apparatus for learning or determining delays between neuron models so that the uncertainty in input spike timing is accounted for in the margin of time between a delayed pre-synaptic input spike and a post-synaptic spike. In this manner, a neural network can correctly match patterns (even in the presence of significant jitter) and correctly distinguish between different noisy patterns. One example method generally includes determining an uncertainty associated with a first pre-synaptic spike time of a first neuron model for a pattern to be learned; and determining a delay based on the uncertainty, such that the delay added to a second pre-synaptic spike time of the first neuron model results in a causal margin of time between the delayed second pre-synaptic spike time and a post-synaptic spike time of a second neuron model.

Abstract: A system for estimating a strain of a component and method of estimating strain is provided. The system includes a signal generator configured to transmit a signal toward the component. A sensor is coupled to the component and configured to receive the signal and to generate a reflected signal. The system includes a fiber Bragg grating filter coupled to the sensor and configured to filter the reflected signal and to generate a filtered signal. A detector is coupled to the filter and configured to convert the filtered signal to a time domain signal. The system includes an artificial neural network coupled to the detector and configured to process the time domain signal to facilitate estimating the strain of the component.

Abstract: System and methods for providing a cognitive network (300). Initialization parameters for distributed Multi-Objective Optimization (“MOO”) algorithms are generated based on project requirements. A Pareto Front (100) is determined for each protocol stack layer by solving the distributed MOO algorithms using the initialization parameters. The Pareto Fronts are analyzed in aggregate to develop best overall network solutions. The best overall network solutions are then ranked according to a pre-defined criteria. A top ranked solution is identified for the best overall network solutions that comply with current regulatory and project/mission policies. Subsequently, operations are performed to compute configuration parameters for protocols of the protocol stack layers that enable implementation of the top ranked solution within the cognitive network. Network resources of the protocol stack layers are then configured in accordance with the configuration parameters.

Abstract: Provided is a data processing apparatus that may include a storage unit, a first calculator, and a second calculator. The storage unit may store a plurality of training data obtained by motion sensing. The first calculator may calculate a first transformation matrix by performing a regression analysis for the plurality of training data. The second calculator may calculate first output data by applying the first transformation matrix to first input data.

Abstract: A determination device includes a region information recording unit that records therein region information regarding a closed region corresponding to a data distribution shape of a same category within a feature space, the closed region being formed by a plurality of nodes and line segments connecting the plurality of nodes. The determination device also includes a category deciding unit that decides a category of a determination target based on the region information and a position of the determination target within the feature space.

Abstract: A delay generator comprises at least one programmable resistor RPCM made of a chalcogenide-based phase-change material, said resistor RPCM being initialized, so as to generate a delay, in a way such that the resistance of the resistor RPCM equals a pre-set initial value R0 and such that the chalcogenide is in the amorphous phase, and a comparator comparing a reference electrical quantity that is stable over time with a variable electrical quantity representative of the resistance of the programmable resistor RPCM, the comparator generating a singularity signal s, said singularity being generated when the difference between the two electrical quantities changes sign.

Abstract: According to various embodiments, a ratings matrix including matrix values is generated, each row of the ratings matrix identifying one of a plurality of users, each column of the ratings matrix identifying one of a plurality of items, and each of the matrix values corresponding to a known affinity rating describing a degree of affinity associated with one of the users and one of the items. The ratings matrix may include a missing entry representing an unknown affinity rating. According to various embodiments, a revised ratings matrix is generated by factoring the ratings matrix into a user matrix and an item matrix, the revised ratings matrix being the product of the user matrix and the item matrix and including at least one entry representing a predicted affinity rating in place of the missing entry.

Abstract: A method and apparatus for providing personalized configuration of physical supports for the human body, comprising accepting input including an individual's demographic information, neurological attributes, physical history, operational environment, and outcome or use objectives, processing user input employing an artificial intelligence engine, and then returning guidance and/or control parameters directed to seating adjustment and positioning, including incline angles for wheelchair tilt and recline.

Abstract: A system for prospectively identifying media characteristics for inclusion in media content is disclosed. A neural network database including media characteristic information and feature information may associate relationships among the media characteristic information and feature information. Personal characteristic information associated with target media consumers may be used to select a subset of the neural network database. A first set of nodes, representing selected feature information, may be activated. The node interactions may be calculated to detect the activation of a second set of nodes, the second set of nodes representing media characteristic information. Generally, a node is activated when an activation value of the node exceeds a threshold value. Media characteristic information may be identified for inclusion in media content based on the second set of nodes.

Abstract: An extensible adaptive classification framework and method can include multiple feature detection modules, and a platform for integrating the multiple feature detection modules utilizing a plurality of AHaH nodes as adaptive classifiers over a feature space of multiple and extensible feature factory modules, thereby configuring the platform as an extensible and continuously adaptive pattern recognition platform.

Abstract: In some aspects of the present application, a method for identifying significant events related to machine problems. The method includes receiving one or more machine problems; determining one or more machine problem classifications based on the one or more machine problems; generating a probability distribution that the one or more machines problems are related to the one more machine problem classifications; determining if one or more events are associated with the one or more machine problems during a predetermined time interval; and determining if the one or more events are significantly related to the one or more machine problem classifications using a statistical algorithm.

Abstract: A ranking approach is used to determine rank-based relationships. In connection with various embodiments, the present invention is directed to a method for ranking nodes of a graph. A vector is provided as a function of a set of random parameters, and a probability matrix function is used, relative to nodes of the graph, to assess the statistics of the vector that solves a probability-based system. Certain embodiments are directed to determining a page rank for a web-based search.

Abstract: Systems and methods for selecting an appropriate caching algorithm to be used when temporarily storing data accessed by an executing application using a neural network may dynamically and/or iteratively replace an initial caching algorithm being used for the application. An input layer of the neural network may gather values of performance related parameters, such as cache hit rates, data throughput rates, or memory access request response times. The neural network may detect a pattern or change in a pattern of accesses, or a change in a workload, a hardware component, or an operating system parameter. Dependent on these and/or other inputs, the neural network may select and apply a caching algorithm likely to improve performance of the application. Other inputs to the neural network may include values of hardware configuration parameters and/or operating system parameters. The neural network may perform a training exercise or may be self-training, e.g., using reinforcement learning.

Abstract: Methods and systems may support conclusions of a clinician by enabling the clinician to arbitrarily define the symptoms according to the patient's record. The method may comprise: (a) determining a plurality of symptoms representing a patient and including characteristics of the patient, the symptoms being categorized as present symptoms, absent symptoms or open symptoms; (b) establishing a multi-tier relationship between said symptoms and a plurality of diseases based on a knowledge model; (c) adjusting weighting factor(s) for at least one multi-tier relationship based on said knowledge model; (d) optionally adjusting at least one weighting factor of step (c) by an expert; and (e) building a ranking of diseases from said multi-tier relationship based on said weighting factors. The method may provide an efficient ranking of disease information, thereby supporting a clinical diagnosis that may consider multiple symptoms while emphasizing particular symptoms in view of the clinician's expertise.

Abstract: Certain example embodiments described herein relate to techniques for dynamically selecting rule processing modes. The processing mode does not need to be specified during rule design/authoring. Two sets of artifacts may be generated to support a desired processing mode. This may occur in the designer's local workspace, e.g., so that rule invocation can be tested locally. Additionally, or alternatively, both sets of artifacts may be installed on the rule engine running on a remote server when the project is deployed. The designer need not be aware that both sets of artifacts are being generated. In certain example embodiments, the designer may have the ability to sequence rules within metaphors (or decision entities such as decision tables), and/or the ability to sequence metaphors within rule sets. During rule invocation, a parameter may be provided to indicate the processing mode (e.g., sequential or inferential) to be used by the rule engine.

Abstract: Some embodiments of using left and right unlinking by an example rule engine have been presented. A rule engine can create a network having a number of nodes to evaluate a set of rules in a knowledge base. The rule engine may initialize a session to be processed using the network to allow each of the nodes to be logically left unlinked and logically right unlinked at the same time during the session.