Abstract: A sensor system comprises: an energy storage device; an intermittent energy release device electrically coupled to the energy storage device, wherein the intermittent energy release device causes the energy storage device to release stored energy intermittently; a sensor electrically coupled to the energy storage device; a register electrically coupled to the sensor, wherein the register stores readings from the sensor; a synaptic neural network core electrically coupled to the sensor, wherein the synaptic neural network core converts the readings from the sensor into a synthetic context-based object that is derived from the readings and a context object; a transponder electrically coupled to the synaptic neural network core; and a storage buffer within the transponder, wherein the storage buffer stores the synthetic context-based object for transmission by the transponder to a monitoring system.

Abstract: A modular quantum computer architecture is developed with a hierarchy of interactions that can scale to very large numbers of qubits. Local entangling quantum gates between qubit memories within a single modular register are accomplished using natural interactions between the qubits, and entanglement between separate modular registers is completed via a probabilistic photonic interface between qubits in different registers, even over large distances. This architecture is suitable for the implementation of complex quantum circuits utilizing the flexible connectivity provided by a reconfigurable photonic interconnect network. The subject architecture is made fault-tolerant which is a prerequisite for scalability.

Abstract: Embodiments of the invention relate to a time-division multiplexed neurosynaptic module with implicit memory addressing for implementing a universal substrate of adaptation. One embodiment comprises a neurosynaptic device including a memory device that maintains neuron attributes for multiple neurons. The module further includes multiple bit maps that maintain incoming firing events for different periods of delay and a multi-way processor. The processor includes a memory array that maintains a plurality of synaptic weights. The processor integrates incoming firing events in a time-division multiplexing manner. Incoming firing events are integrated based on the neuron attributes and the synaptic weights maintained.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing a layer output for a convolutional neural network layer, the method comprising: receiving a plurality of activation inputs; forming a plurality of vector inputs from the plurality of activation inputs, each vector input comprising values from a distinct region within the multi-dimensional matrix; sending the plurality of vector inputs to one or more cells along a first dimension of the systolic array; generating a plurality of rotated kernel structures from each of the plurality of kernel; sending each kernel structure and each rotated kernel structure to one or more cells along a second dimension of the systolic array; causing the systolic array to generate an accumulated output based on the plurality of value inputs and the plurality of kernels; and generating the layer output from the accumulated output.

Abstract: A synapse circuit to perform spike timing dependent plasticity (STDP) operation is provided. The synapse circuit includes a memristor having a resistance value, a transistor connected to the memristor, and the transistor configured to receive at least two input signals. The resistance value of the memristor is changed based on a time difference between the at least two input signals received by the transistor.

Abstract: A method, system, and/or computer program product performs rule execution in decision services. One or more specialized rulesets classified by decision partitions are based on defined clustering predicates of decision service signatures for business rules. A decision request is received from a client, and one or more parameters of the decision request are input to a clustering predicate based on decision service signatures to produce a decision category. A specialized ruleset for the decision request is determined based on the decision category, and the decision request is forwarded for processing to the specialized ruleset. A decision input is then returned from the specialized ruleset.

Abstract: A production rules engine comprises: a class loader for loading a production rule ontology into a rule engine; a class loader for loading production rules into the rule engine, wherein a production rule comprises a rule and an action defined in the production rule ontology; instance creation logic for creating instances of production rules; a reasoner for executing the production rules and for locating an instance of a production rule having an inconsistency between an action to change the ontology and the existing ontology and for executing the production rules after inconsistencies have been fixed; a constraint engine for locating a solution to an inconsistent ontology; and a fixer for updating the inconsistent ontology with the located solution.

Abstract: In one aspect, the invention concerns a method of operating a chatbot to engage in a conversation with a correspondent the method comprises building a profile having plural profile variables for the correspondent; and during the conversation with the correspondent; selecting a node in the conversation data structure for processing based on the one or more profile variables, and processing the node to follow a conversation path based on the node's coded instructions and/or relationship with other nodes. In another aspect, the method comprises the steps of attempting to match the received input message with a node in the conversation data structure of the chatbot; if a matched node is found, selecting the matched node for processing; but if a matched node is not found, selecting a node for processing using a fuzzy search, or using a default procedure.

Abstract: Technical solutions are described for implementing a neural network. An example system includes a crosspoint array including a plurality of nodes, each node representing a weight assigned to a neuron of the neural network. The system also includes a capacitor associated with a set of nodes from the plurality of nodes, where the capacitor is configured to store a current value corresponding to a sum of outputs from each respective node from the set of nodes. The system also includes a clocking circuit that initiates a forward pass to propagate the current value stored in the capacitor to a subsequent layer of the neural network. The clocking circuit further initiates a backward pass to propagate the current value stored in the capacitor to a preceding layer of the neural network. The clocking circuit further initiates a weight-update pass to update the weights in the neural network.

Abstract: Embodiments of an apparatus and method for assessing non-kinetic weapon performance for negating missile threats are generally described herein. In some embodiments, vulnerabilities of missile threats and techniques for negating the threats are identified. A probability of negation associated with an effectiveness of each of the techniques against the vulnerabilities is calculated. The calculated probability of negation of each technique against each vulnerability are conditioned at a plurality of times associated with a plurality of asymmetric missile defense (AMD) layer elements to produce temporal level probabilities of negation. Each temporal level probabilities of negation are conditioned based on a probability of validation of deployment and a probability of verification of mitigation to produce a battle damage assessment probability of negation.

Abstract: Method, system, and computer program product to analyze a plurality of candidate answers identified as responsive to a question presented to a deep question answering system, by computing a first feature score for a first feature of an item of evidence, of a plurality of items of evidence, the first feature score being based on at least one attribute of the first feature, the item of evidence relating to a first candidate answer, of the plurality of candidate answers, and computing a merged feature score for the first candidate answer by applying the first feature score to a second feature score for a second feature of the item of evidence.

Abstract: A system includes a free itemset generation unit to generate a set of free itemsets, each having a frequency in the database greater than or equal to a predetermined threshold value set in advance, a valid rule candidate generation unit to generate rule candidates and store the generated rule candidates, and a rule minimality decision unit to check minimality of each of the generated rule candidates and output the generated rule candidate to an output apparatus when the generated rule candidate is determined to be minimal.

Abstract: A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for utilizing temporal indicators to weight semantic values. A set of temporal characteristics is identified of a set of initial candidate answers. For each initial candidate answer in the set of initial candidate answers: a distance value is generated for each of the set of temporal characteristics of the set of initial candidate answers, a multiplier value is determined with which to weight an initial confidence score associated with the initial candidate answer using the distance value; a sentiment value is determined of the initial candidate answer, and a final weight value is determined using the multiplier value, the sentiment value, and the initial confidence score associated with the initial candidate answer. A set of temporally refined candidate answers is then provided using the determined final weight values.

Abstract: System, method, and computer program product to identify relevant features in a deep question answering system, by classifying a first case received by the deep question answering system, and, while training the deep question answering system to answer the first case, identifying a first feature in the first case, computing a first feature score for the first feature, the first feature score indicating a relevance of the first feature in generating a correct response to the first case, and, identifying the first feature as relevant in answering the classified first case upon determining that the first feature score exceeds a relevance threshold.

Abstract: A device, comprising: an array of cells, wherein the cells are arranged in columns and rows; wherein each cell comprises a memristive device; an interfacing circuit that is coupled to each cell of the array of cells; wherein the interfacing circuit is arranged to: receive or generate first variables and second variables; generate memristive device input signals that once provided to memristive devices of the array will cause a change in a state variable of each of the memristive devices of the cells of the array, wherein the change in the state variable of each of the memristive devices of the cells of array reflects a product of one of the first variables and one of the second variables; provide the memristive device input signals to memristive devices of the array; and receive output signals that are a function of at least products of the first variables and the second variables.

Abstract: The subject disclosure is directed towards crowd-based approach to boosting the correctness of a computer program. Results from candidate programs obtained from a first crowd and which may be blended with one another into synthesized programs are sent to a second crowd for evaluation. Based upon the results, a training set evolves and programs are filtered based upon fitness. The process of blending and fitness evaluation with an evolved training set may be iteratively repeated to find a most fit program.

Abstract: A method is used in managing knowledge-based authentication systems. Questions are created from organization based information. The questions are evaluated based on a set of parameters. Based on the evaluation, a set of questions is selected from the questions and a set of responses is selected for each question of the set of questions for a scenario. A user is authenticated in the scenario using the set of questions.

Abstract: Method, system, and computer program product to analyze a plurality of candidate answers identified as responsive to a question presented to a deep question answering system, by computing a first feature score for a first feature of an item of evidence, of a plurality of items of evidence, the first feature score being based on at least one attribute of the first feature, the item of evidence relating to a first candidate answer, of the plurality of candidate answers, and computing a merged feature score for the first candidate answer by applying the first feature score to a second feature score for a second feature of the item of evidence.

Abstract: A method of validating rules configured to be utilized in an information extraction application, including: receiving a plurality of labeled samples in a training database; for each of the rules in the rule database: (a) determining, for each of the data points of the plurality of labeled samples in the training database to which the rule applies, whether applying the rule to the data point has a positive or negative impact on matching an output for the data point based on the rule to the assured output of the labeled sample corresponding to the data point; (b) generating positive impact information for the rule based on the positive voters; (c) generating negative impact information for the rule based on the negative voters; and (d) determining a metric for the rule based on the quantity of the negative voters and the quantity of the positive voters; ranking the rules based on the metrics corresponding to the rules; and sending to a user for refinement one or more flagged rules of the rules that have a lowes

Abstract: A nonlinear neuron classifier comprising a neuron array including a plurality of neuron chips each including a plurality of neurons of variable length and variable depth, the chips processing input vectors of variable length and variable depth that are input into the classifier for comparison against vectors stored in the classifier, wherein an NSP flag is set for a plurality of the neurons to indicate that only that plurality of neurons is to participate in the vector calculations. A virtual content addressable memory flag is set for certain of the neuron chips to enable functions including fast readout of data from the chips. Results of vector calculations are aggregated for fast readout for a host computer interfacing with the classifier.