Abstract: Provided is an information processing apparatus including: a reward estimator generating unit using action history data, which includes state data expressing a state of an agent, action data expressing an agent's action, and a reward value expressing a reward of the action, as learning data to generate, through machine learning, a reward estimator estimating the reward value from inputted state data and action data; an action selecting unit preferentially selecting an action not included in the action history data but with a high estimated reward value; and an action history adding unit causing the agent to perform the selected action and adding to the action history data the state data and action data for the action and the action's reward value in association with each other. The reward estimator is regenerated when a set of state data, action data, and the reward value is added to the action history data.

Abstract: Embodiments of the invention provide a neural core circuit comprising a synaptic interconnect network including plural electronic synapses for interconnecting one or more source electronic neurons with one or more target electronic neurons. The interconnect network further includes multiple axon paths and multiple dendrite paths. Each synapse is at a cross-point junction of the interconnect network between a dendrite path and an axon path. The core circuit further comprises a routing module maintaining routing information. The routing module routes output from a source electronic neuron to one or more selected axon paths. Each synapse provides a configurable level of signal conduction from an axon path of a source electronic neuron to a dendrite path of a target electronic neuron.

Abstract: The present invention provides a method for generating a decision tree for determining the type of an internal abnormality of an oil-filled electric apparatus using a computer. In the decision tree generation method, the computer generates a standardized data group by converting concentrations of a plurality of gas species dissolved in an insulating oil in an oil-filled electric apparatus into ratios for each abnormality case, generates a discretized data group by converting the ratios of the concentrations of the gas species, the ratios constituting the standardized data group, into a plurality of discretized attributes using predetermined thresholds which are set for the respective gas species, and generates a decision tree for determining the type of an internal abnormality of the oil-filled electric apparatus by analysis using specific formulae on the basis of the discretized data group.

Abstract: Certain embodiments of the present disclosure support implementation of a digital neural processor with discrete-level synapses and probabilistic synapse weight training.

Abstract: A system and a method for a service engine providing distributed intelligent assistance to a user are described herein. The method comprising steps of receiving and displaying a user inquiry from the user, the user inquiry having a linguistic pattern including a verb; generating and displaying a follow up question based on the user inquiry; receiving and displaying a follow up answer from the user; and generating and displaying a response based on the user inquiry and the follow up answer.

Abstract: Methods, systems, and computer storage media are provided for predicting a probability of acute deterioration for a specific patient. Various discrete measurements are taken regarding the patient's current health. Those measurements are used to determine a PPOD score, which is displayed for clinicians.

Abstract: A computer-implemented method, comprises extracting a measure from a content article representing a probability that the article relates to a topic, allocating the article to a group of articles relating to at least one topic on the basis of the measure, using a set of social media objects relating to the article to extract a measure representing a sentiment for the article, and aggregating respective measures for the sentiment of articles in the group to provide an aggregate measure.

Abstract: The present disclosure is directed to systems and methods that score content, URLs, domains, phrases or any entity based on an expected relevance to an individual user which may be based on that user's previous engagement with digital resources. A server receives identification of a plurality of actions of a user, which may include a click by the user on a link associated with a digital resource of a plurality of digital resources. The server may receive identification of actions of the user to share one or more digital resources of the plurality of digital resources. The server may identify a plurality of keywords from content of the plurality of digital resources, classify patterns from the actions of the users and the keywords and generate, based on the pattern classification, a relevance score responsive to receiving a user identifier and a digital resource keyword.

Abstract: Systems and methods for determining predictive model types are provided. A method may include generating a predictive model for a web page of a website, wherein the web page includes a configuration defining one or more objects presented with the web page, and wherein each object is associated with a predictive model. The method may include determining one or more predictive model types that are associated with the predictive model, determining one or more performance indicators that correspond to each determined predictive model type, wherein performance indicators represent one or more benefits to a website, selecting a predictive model type of the predictive model out of the one or more predictive model types, wherein the predictive model type is selected based on a performance indicator corresponding to the selected predictive model type, and determining a configuration of the web page using the selected predictive model type of the predictive model.

Abstract: An anticipatory monitoring and prediction system can include methods for generating effective, accurate predictions of other traffic objects in the vicinity of an ego-car. The invention proposes to combine approximate probability distributions (ADPs) of agent states with Attractor Functions (AFs) for generating distributed probabilistic representations of the potential future states of the observed traffic objects. AFs are selected based on both the current road context, in which the ego-car is situated, and the current states of all participating objects. The generated predictions can be used to filter incoming sensory information for better object state estimations, rate the nature of the behavior of other traffic objects by comparing generated predictions with actual perceived sensor information, or infer accident likelihoods by comparing the predicted state distributions of objects and the ego-car. Warning and information signals or control commands can be issued in a driving assistance system.

Abstract: There is provided an information processing apparatus including a reward estimator generator using action history data, including state data expressing a state, action data expressing an action taken by an agent, and a reward value expressing a reward obtained as a result of the action, as learning data to generate, through machine learning, a reward estimator estimating a reward value from inputted state data and action data. The reward estimator generator includes: a basis function generator generating a plurality of basis functions; a feature amount vector calculator calculating feature amount vectors by inputting state data and action data in the action history data into the basis functions; and an estimation function calculator calculating an estimation function estimating the reward value included in the action history data from the feature amount vectors according to regressive/discriminative learning. The reward estimator includes the plurality of basis functions and the estimation function.

Abstract: Provided is a method of determining command line validity, including: a step of maintaining a block network address database including block network address information; a step of receiving a command line from a terminal of a user; a step of extracting network address information included in the command line; a step of determining whether the network address information is the block network address information, with reference to the block network address database; a step of generating log information associated with the command line in case that the network address information is not the block network address information as the result of the determination, in which the log information comprises at least one of the network address information included in the command line, input time point information with respect to the input time point of the command line, and request content information; a step of recording the log information in a log database; and a step of determining the validity of the command line by u

Abstract: A system for evaluating communicative acts to determine a social perception network based on communicative acts between a plurality of communicative pairs. Each communicative pair includes two communicating entities. The system includes a patterns database, a scoring processor, and a communications network aggregation processor. The patterns database stores behavior recognition patterns defining particular behaviors and a score associated with each of the particular behaviors. The scoring processor is configured to determine a pairwise social perception score for the communicative pair based on the particular behaviors identified in the communicative acts. The scoring processor is configured to determine a different pairwise social perception score for each one of the plurality of communicative pairs. The communications network aggregation processor is configured to combine the pairwise social perception scores for each of the plurality of communicative pairs into a social perception network.

Abstract: To provide a latent variable model estimation apparatus capable of implementing the model selection at high speed even if the number of model candidates increases exponentially as the latent state number and the kind of the observation probability increase. A variational probability calculating unit 71 calculates a variational probability by maximizing a reference value that is defined as a lower bound of an approximation amount, in which Laplace approximation of a marginalized log likelihood function is performed with respect to an estimator for a complete variable. A model estimation unit 72 estimates an optimum latent variable model by estimating the kind and a parameter of the observation probability with respect to each latent state. A convergence determination unit 73 determines whether a reference value, which is used by the variational probability calculating unit 71 to calculate the variational probability, converges.

Abstract: A method of operation of a navigation system includes: generating a training data from a randomly sampled uncategorized point of interest; generating a trained classifier model by training a classifier model using the training data; generating a category identifier, a confidence score, or a combination thereof for an uncategorized point of interest using the trained classifier model; generating a categorized point of interest by assigning the category identifier to the uncategorized point of interest; calculating a weighted confidence score based on a weighted F-measure for the category identifier, a pair of the category identifier and the confidence score; and consolidating the categorized point of interest based on the weighted confidence score for the category identifier being meeting or exceeding a threshold for displaying on a device.

Abstract: To entities that are likely to engage in a behavior, a behavior discrimination threshold for each of a plurality of behavior variables is determined. Variable values for each entity of a plurality of target entities and for each of the behavior variables are compared to the relevant behavior discrimination threshold to provide identifying variables for each entity. An index value is determined for each of the plurality of target entities based on the identifying variables for that entity. An index threshold is determined such that those entities of the target entities having index values that meet or exceed the index threshold are likely to exhibit or engage in the behavior more frequently than a random sampling of the plurality of training entities. Actions designed to affect the likelihood that the resulting targeted entities will engage in the behavior may be directed to the targeted entities.

Abstract: A component in a graph-based computation having data processing components connected by linking elements representing data flows is updated by receiving a rule specification, generating a transform for transforming data based on the rule specification, associating the transform with a component in the graph-based computation, and in response to determining that a new rule specification has been received or an existing rule specification has been edited, updating the transform associated with the component in the graph-based computation according to the new or edited rule specification. A computation is tested by receiving a rule specification including a set of rule cases, receiving a set of test cases, each test case containing a value for one or more of the potential inputs, and for each test case, identifying one of the rule cases that will generate an output given the input values of the test case.

Abstract: A fractal flow fabric can include a substrate for growing at least one procedure, and a plurality of nodes formed on said substrate, wherein each node among said plurality of nodes connects to each other through at least one flow-stabilized link to grow said at least one procedure and automatically solve a problem via said at least one procedure.

Abstract: The invention provides a computer-implemented chunking process (named “OP”) to assign and physically associate unique spatial representations (“chunk codes”) in one representational (coding) space (“chunk coding space”) with unique temporal sequences of spatial codes (“items”) in another coding space (“item coding space”). OP differs from all prior chunking processes in that, for any particular item sequence, it activates a unique chunk code for that sequence during presentation of that sequence's first item, even if other sequences from the input domain may begin with the same item.

Abstract: Embodiments of the invention provide a neural network comprising multiple functional neural core circuits, and a dynamically reconfigurable switch interconnect between the functional neural core circuits. The interconnect comprises multiple connectivity neural core circuits. Each functional neural core circuit comprises a first and a second core module. Each core module comprises a plurality of electronic neurons, a plurality of incoming electronic axons, and multiple electronic synapses interconnecting the incoming axons to the neurons. Each neuron has a corresponding outgoing electronic axon. In one embodiment, zero or more sets of connectivity neural core circuits interconnect outgoing axons in a functional neural core circuit to incoming axons in the same functional neural core circuit.