Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training machine learning systems. One of the methods includes receiving a plurality of training examples; and training a machine learning system on each of the plurality of training examples to determine trained values for weights of a machine learning model, wherein training the machine learning system comprises: assigning an initial value for a regularization penalty for a particular weight for a particular feature; and adjusting the initial value for the regularization penalty for the particular weight for the particular feature during the training of the machine learning system.

Abstract: To suggest new connections to a user of a social networking system, the system generates a set of candidate users to whom the user has not already formed a connection. The system determines the likelihood that the user will connect to each candidate user if suggested to do so, and it also computes the value to the social networking system if the user does connect to the candidate user. Then, the system computes an expected value score for each candidate user based on the corresponding likelihood and the value. The candidate users are ranked and the suggestions are provided to the user based on the candidate users' expected value scores. The social networking system can suggest other actions to a user in addition to forming a new connection with other users.

Abstract: In one embodiment, one or more reporting nodes are selected to report network metrics in a network. From a monitoring node in the network, a trigger message is sent to the one or more reporting nodes. The trigger message may trigger the one or more reporting nodes to report one or more network metrics local to the respective reporting node. In response to the trigger message, a report of the one or more network metrics is received at the monitoring node from one of the one or more reporting nodes.

Abstract: Embodiments relate to facilitating a meeting. A method for reducing an amount of communications to analyze in order to determine a cognitive state of an entity is provided. The method determines a first likelihood of an entity to have a particular cognitive state based on a set of physiological measures of the entity. The method receives communications from the entity. The method generates a graph of communications of the entity. The method performs a graphical text analysis on the graph to determine a second likelihood of the entity to have the particular cognitive state. The method determines whether the entity has the particular cognitive state based on the first likelihood and the second likelihood.

Abstract: Aspects of the disclosure provide a method for configuring a Quantum Annealing (QA) device. Then QA device has a plurality of qubits and a plurality of couplers at overlapping intersections of the qubits. The method includes mapping a node of a neural network that have a plurality of nodes and connections between the nodes to a qubit in the QA device, and mapping a connection of the neural network to a coupler at an intersection in the QA device where two qubits corresponding to two nodes connected by the connection intersect. The method further includes mapping a node of the neural network to a chain of qubits. In an embodiment, a coupling between qubits in the chain is configured to be a ferromagnetic coupling in order to map the node of the neural network to the chain of qubits.

Abstract: A system for communicating postsynaptic neuron states. The system includes a first neuromorphic core and a second neuromorphic core. The first neuromorphic core includes a first array of synaptic memory cells and postsynaptic neuron circuits. Each of the postsynaptic neuron circuits is coupled to a row of synaptic memory cells in the first array of synaptic memory cells. Each of the postsynaptic neuron circuits is configured to fire when voltage sensed from the row of synaptic memory cells exceeds a threshold. The second neuromorphic core includes a second array of synaptic memory cells. A neuron bus is configured to serially transmit indications of a postsynaptic neuron circuit fire from the first neuromorphic core to the second neuromorphic core.

Abstract: A system for assisting a user in determining a cause of a manufacturing non-conformance situation in a manufacturing application. The system may include an associative memory subsystem that is populated with a plurality of entity types, with each entity type including at least one entity, to form an associative memory. A user input device enables a user to input manufacturing non-conformance information into the associative memory subsystem that causes the associative memory subsystem to perform an initial search. The initial search generates a plurality of the entities that has a primary relevance useful for investigating the manufacturing non-conformance situation. An output device is responsive to the associative memory subsystem presents the plurality of entities found during the initial search to the user.

Abstract: Embodiments relate to facilitating a meeting. A method for reducing an amount of communications to analyze in order to determine a cognitive state of an entity is provided. The method determines a first likelihood of an entity to have a particular cognitive state based on a set of physiological measures of the entity. The method receives communications from the entity. The method generates a graph of communications of the entity. The method performs a graphical text analysis on the graph to determine a second likelihood of the entity to have the particular cognitive state. The method determines whether the entity has the particular cognitive state based on the first likelihood and the second likelihood.

Abstract: A computerized method for creating a function model based on a non-parametric, data-based model, e.g., a Gaussian process model, includes: providing training data including measuring points having one or multiple input variables, the measuring points each being assigned an output value of an output variable; providing a basic function; modifying the training data with the aid of difference formation between the function values of the basic function and the output values at the measuring points of the training data; creating the data-based model based on the modified training data; and providing the function model as a function of the data-based model and the basic function.

Abstract: A method and system for constructing a classifier for a set of records to be classified (108) into predicted classes (351-353) are provided. The set of records that are to be classified (108) are clustered into a plurality of clusters. A first classifier (106) is created that classifies records into the plurality of clusters (321-323) and the first classifier (106) is applied to a set of training records (110), each of the training records (331-334) having a predicted class (306). A classifier (107A-C) may then be created for each sub-set of training records (341-343) classed into each of the plurality of clusters and the classifier (107A-C) applied to a sub-set of records to be classified (311-313) formed in the corresponding cluster.

Abstract: A character class is detected in a regular expression and substituted with a pseudo character. A table is created with a bit vector for each pseudo character inserted into the regular expression. Each bit in the bit-vector represents one character of the alphabet from which the expression is generated. The status of the bits in a bit-vector indicates which characters of the alphabet are included in the character class. The pseudo character in the modified regular expression is used to construct a non-deterministic finite automaton (NFA). The NFA with the pseudo character is then used to construct a deterministic finite automaton (DFA). When constructing the DFA, the bit-vectors are used to determine if a certain transition should be constructed in the DFA.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting the accuracy of user submissions. One of the methods includes receiving, from a user, an update to an attribute of an entity related to a topic. If the user is determined to be reliable relative to the topic based on user profile data of the user, the knowledge base is updated with the update to the attribute of the entity.

Abstract: Embodiments of the invention relate to a scalable neural hardware for the noisy-OR model of Bayesian networks. One embodiment comprises a neural core circuit including a pseudo-random number generator for generating random numbers. The neural core circuit further comprises a plurality of incoming electronic axons, a plurality of neural modules, and a plurality of electronic synapses interconnecting the axons to the neural modules. Each synapse interconnects an axon with a neural module. Each neural module receives incoming spikes from interconnected axons. Each neural module represents a noisy-OR gate. Each neural module spikes probabilistically based on at least one random number generated by the pseudo-random number generator unit.

Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of layers, the circuit comprising: activation circuitry configured to receive a vector of accumulated values and configured to apply a function to each accumulated value to generate a vector of activation values; and normalization circuitry coupled to the activation circuitry and configured to generate a respective normalized value from each activation value.

Abstract: An analytic network process (ANP) storage memory stores an ANP weighted supermatrix representing an ANP model. A processor is in communication with the ANP storage memory. The processor is configured to change priorities of a node in the ANP weighted supermatrix to be more important, to change priorities of the node in the ANP weighted supermatrix to be less important, and to assess a sensitivity of the node which was changed relative to the ANP model. The processor further is configured to maintain a same proportionality in the ANP weighted supermatrix for the changing of the priorities and the assessing of the relative sensitivity.

Abstract: The present invention provides a method and system for constructing one or more a comprehensive summaries of event sequence(s). The present invention approaches the problem of finding the shortest yet most comprehensive summary of an event sequence by transforming this summarization problem into a concrete optimization problem and provides a computer-implementing technique for solving this optimization problem to construct and/or form the basis for constructing the summaries. The summaries describe an entire event sequence while at the same time reveal local associations between events of that sequence. In certain embodiments, the segmentation of the event sequence produced in accordance with the present invention is itself a summary of the event sequence. In other embodiments, the segmentation produced forms a basis for one or more summaries.

Abstract: Some embodiments of alpha node hashing in an exemplary rule engine have been presented. In one embodiment, constraints are added into a constraint set in response to requests from one or more users of a rule engine. The rule engine then determines which constraints within the constraint set are mutually exclusive. Furthermore, the rule engine dynamically enables hashing of facts asserted into a working memory of the rule engine in response to a current number of the mutually exclusive constraints.

Abstract: A system for classification of a test object using a training set comprising a plurality of objects, each of which is assigned as a member of a class. Collectively, the objects in the training set are members of at least two classes. A computer system is configured as a probabilistic classifier. The classifier estimates the probability of the test object being a member of each of the classes in the training set. The probabilistic classifier estimates the probability with reference to the class assignments of the objects in the training set which are neighbors to the test object within a defined region within the training set. The probabilistic classifier takes into account the situation in which there is an imbalance in the number of objects in the different classes in the training set. Additionally, the probabilistic classifier does not require any knowledge of the probability distribution function of the classes in the training set.

Abstract: A method for predicting survival rates of medical patients includes providing a set D of survival data for a plurality of medical patients, providing a regression model having an associated parameter vector ?, providing an example x0 of a medical patient whose survival probability is to be classified, calculating a parameter vector {circumflex over (?)} that maximizes a log-likelihood function of ? over the set of survival data, l(?|D), wherein the log likelihood l(?|D) is a strictly concave function of ? and is a function of the scalar x?, calculating a weight w0 for example x0, calculating an updated parameter vector ?* that maximizes a function l(?|D?{(y0,x0,w0)}), wherein data points (y0,x0,w0) augment set D, calculating a fair log likelihood ratio ?f from {circumflex over (?)} and ?* using ?f=?(?*|x0)+sign(?({circumflex over (?)}|x0)){l({circumflex over (?)}|D)?l(?*|D)}, and mapping the fair log likelihood ratio ?f to a fair price y0f, wherein said fair price is a probability that class label y0 for exam

Abstract: The subject invention relates to integrating agents, control logic, and simulations in order to simulate and validate a control strategy for a physical system. The systems and methods integrate agents and control logic with simulations, and utilize the integrated agents, control logic, and simulations to generate a proxy. The proxy can be employed to couple one or more controllers executing the agents and control logic with the simulations. Visualization is utilized to visualize the simulation, including the agents and the control logic. In addition, the systems and methods utilize a synchronization algorithm to synchronize the execution times of the controllers and the simulations. The foregoing mitigates validation through building and testing physical system and/or test beds. Upon validating control strategies, associated agents and logic can be loaded in one or more industrial controllers controlling the physical system, and the simulation can be utilized to represent the physical system.