Abstract: A long-term personal agent program, executable as network service and/or on one or more user computing devices and related method for identifying opportunities and making recommendations on behalf of one or more users, are disclosed herein. In one example, the personal agent program includes a monitoring engine configured to monitor and interpret a user's activities over time with a plurality of sensing and logging methodologies according to user authorization, the use of statistical methods for learning to understand a user's goals and behavioral patterns from data, and the use of procedures for computing the expected value of information guiding sensing and logging in different contexts. The personal agent further may include a recommendation methodology configured to make suggestions and to take actions on behalf of the user, in the present moment as well as for future times, based on inferences about user goals and opportunities in the world.

Abstract: Techniques are described herein for predicting one or more behaviors by an email recipient and, more specifically, to machine learning techniques for predicting one or more behaviors of an email recipient, changing one or more components in the email to increase the likelihood of a behavior, and determining and/or scheduling an optimal time to send the email. Some advantages of the embodiments disclosed herein may include, without limitation, the ability to predict the behavior of the email recipient and suggest the characteristics of an email which will increase the likelihood of a positive behavior, such as a reading or responding to the email, visiting a website, calling a sales representative, or opening an email attachment.

Abstract: A computing device for use in decision tree computation is provided. The computing device may include a software program executed by a processor using portions of memory of the computing device, the software program being configured to receive user input from a user input device associated with the computing device, and in response, to perform a decision tree task. The computing device may further include a decision tree computation device implemented in hardware as a logic circuit distinct from the processor, and which is linked to the processor by a communications interface. The decision tree computation device may be configured to receive an instruction to perform a decision tree computation associated with the decision tree task from the software program, process the instruction, and return a result to the software program via the communication interface.

Abstract: Incremental model training for advertisement targeting is performed using streaming data. A model for targeting advertisements of an advertising campaign is initialized. A data stream including data corresponding to converters and data corresponding to non-converters is received. The model is then applied to the data corresponding to the converter and data corresponding to the non-converter (or other ratio of converter to non-converters) to obtain a predicted score for each. The predicted score is compared to the observed score (e.g., an observed score of 1 for a converter, and 0 for a non-converter). The difference between the predicted and observed scores is computed, and the model is incrementally updated based on this difference. Models can optionally be built separately on multiple modeling servers that are geographically dispersed in order to support bidding on advertising opportunities in a real-time bidding environment.

Abstract: There is provided an information processing method including inputting a feature quantity vector and an objective variable corresponding to the feature quantity vector, generating a basis function for outputting a scalar quantity by mapping the feature quantity vector, mapping the feature quantity vector using the basis function and calculating the scalar quantity corresponding to the feature quantity vector, evaluating whether or not the basis function used to calculate the scalar quantity is useful for estimating the objective variable using the objective variable along with the scalar quantity and the feature quantity vector corresponding to the scalar quantity, generating an estimation function for estimating the objective variable from the scalar quantity by machine learning on the basis of the scalar quantity and the objective variable corresponding to the scalar quantity using the basis function evaluated to be useful, and outputting the estimation function.

Abstract: A given set of videos are sequenced in an aesthetically pleasing manner using models learned from human curated playlists. Semantic features associated with each video in the curated playlists are identified and a first order Markov chain model is learned from curated playlists. In one method, a directed graph using the Markov model is induced, wherein sequencing is obtained by finding the shortest path through the directed graph. In another method a sampling based approach is implemented to produce paths on the digraph. Multiple samples are generated and the best scoring sample is returned as the output. In a third method, a relevance based random walk sampling algorithm is modified to produce a reordering of the playlist.

Abstract: The system and method of the present invention are described for automatic detection of error in the entry of particular category of individuals, especially referring to gender and age classification either real time while creating a database of such information or on an existing database on the record of individuals by analyzing their biometric characteristics like speech, image or face and other related demographic information like name of the individual in order to accord each individual with a unique identification.

Abstract: The described implementations relate to expressing terminologies in a hierarchical form. One implementation can receive a terminology that can include concept-code pairs. For example, each of the concept-code pairs can include a concept and a code that is assigned to the concept by the terminology. The implementation can map the concepts to levels of a hierarchical ontology, and associate some of the concepts across different levels of the hierarchical ontology. The implementation can also provide programmatic access to the concept-code pairs of the terminology via the hierarchical ontology.

Abstract: An apparatus and method for determining a formation/fluid interaction of a target formation and a target drilling fluid is described herein. The method may include training an artificial neural network using a training data set. The training data set may include a formation characteristic of a source formation and a fluid characteristic of a source drilling fluid and experimental data on source formation/fluid interaction. Once the artificial neural network is trained, a formation characteristic of the target formation and fluid characteristic of target drilling fluid may be input. The formation characteristic of the target formation may correspond to the formation characteristic of the source formation. The fluid characteristic of the target drilling fluid may correspond to the fluid characteristic of the source drilling fluid. A formation/fluid interaction of the target formation and the target drilling fluid may be determined using a value output by the artificial neural network.

Abstract: An apparatus and a method for transmitting and receiving a spike event in a neuromorphic chip. A transmission apparatus of the neuromorphic chip outputs addresses sequentially and repeatedly to an address bus, and when a spike generated by a neuron is detected by the transmission apparatus, outputs a strobe at a first time when one of the addresses being output sequentially and repeatedly becomes identical to an address of the neuron that generated the spike. A receiving apparatus of the neuromorphic chip inputs an address through the address bus at a strobe detection time when the strobe is detected by the receiving apparatus.

Abstract: A method, machine readable storage medium, and system for providing personalized semantic controls for semantic systems. A semantic network may be set up with initial configuration. A business application user interface, including semantic controls, may be coupled to the semantic network to interact with the semantic network. Semantic objects and relations may be defined in the semantic network for business terminology. A user request for business data may be received. The semantic network may update the objects and relations for business terminology based on the request. The business application user interface may provide for personalized semantic controls based on the updated objects and relations.

Abstract: A method detects anomalies in time series data, wherein the time series data is multivariate, by partitioning time series training data into partitions. A representation for each partition in each time window is determined to form a model of the time series training data, wherein the model includes representations of distributions of the time series training data. The representations obtained from partitions of time series test data are compared to the model to obtain anomaly scores.

Abstract: A tractable model solves certain labeling problems by providing potential functions having arbitrary dependencies upon an observed dataset (e.g., image data). The model uses decision trees corresponding to various factors to map dataset content to a set of parameters used to define the potential functions in the model. Some factors define relationships among multiple variable nodes. When making label predictions on a new dataset, the leaf nodes of the decision tree determine the effective weightings for such potential functions. In this manner, decision trees define non-parametric dependencies and can represent rich, arbitrary functional relationships if sufficient training data is available. Decision trees training is scalable, both in the training set size and by parallelization. Maximum pseudolikelihood learning can provide for joint training of aspects of the model, including feature test selection and ordering, factor weights, and the scope of the interacting variable nodes used in the graph.

Abstract: A method of generating a decision graph from event stream data, wherein the event stream data includes a plurality of events, and each event includes an associated time stamp, includes generating decision nodes for the graph, wherein the decision nodes each comprise a question having a temporal element. The method includes generating leaf nodes for the graph, wherein the leaf nodes each comprise a rate parameter, and iteratively splitting and merging nodes in the graph in order to maximize a measure of purity of outcomes in resulting nodes.

Abstract: Systems, apparatus, methods and articles of manufacture provide for implementing a decision engine using a finite state machine for conducting randomized experiments. According to some embodiments, methods may include initializing a decision engine comprising at least one state machine, receiving information defining for the at least one state machine, states and transitions between the states, receiving information defining at least one set of weighted choices, receiving an indication of an occurrence of an event, executing the decision engine to select randomly using the at least one state machine a weighted choice based on the event, and transmitting to the application an indication of the identified random choice.

Abstract: A method of classifying a sample of values related to the use of a server, including: recording, by the server, use events in a log; configuring a classifier tool with a behavioral model formed of a weighted list of parameters, establishing a sample of values from the log, and supplying it to a classifier tool, which calculates a score representative of the adequacy of the sample to a target category, reading recent use events saved in the log and aggregating them over basic time intervals, storing the aggregation result obtained for each basic interval in a distinct record of a first group; aggregating, when the number of records of the first group reaches a threshold, the contents of the records of the first group in a distinct record of a second group, and establishing the sample from the contents of records of the database.

Abstract: In one embodiment, the present invention provides a neural network circuit comprising multiple symmetric core circuits. Each symmetric core circuit comprises a first core module and a second core module. Each core module comprises a plurality of electronic neurons, a plurality of electronic axons, and an interconnection network comprising multiple electronic synapses interconnecting the axons to the neurons. Each synapse interconnects an axon to a neuron. The first core module and the second core module are logically overlayed on one another such that neurons in the first core module are proximal to axons in the second core module, and axons in the first core module are proximal to neurons in the second core module. Each neuron in each core module receives axonal firing events via interconnected axons and generates a neuronal firing event according to a neuronal activation function.

Abstract: A method for operating a sensor based application includes receiving a context hierarchy for the sensor based application, the context hierarchy comprising a plurality of contexts, wherein each of the contexts is assigned a level of interest and a priority, reading the context hierarchy and discovering at least one sensor associated with each of the plurality of contexts, and reading at least one value of each of the sensors, and applying the values.

Abstract: To classify moving images using audio signals. An audio signal is acquired, a section feature relating to an audio frequency distribution is extracted with respect to each of a plurality of sections each having a predetermined length contained in the acquired audio signal, each extracted section feature is compared with each of reference section features to calculate a section similarity indicating a degree of correlation between each section feature and each reference section feature. An integrated feature relating to the plurality of sections and being calculated based on the section similarity calculated with respect to each of the plurality of sections is extracted from the acquired audio signal. The extracted integrated feature is compared with each of one or more reference integrated features, and the audio signal is classified based on comparison result. Then, classification result is used for moving image classification.

Abstract: Disclosed herein are methods for transforming numerical output of mathematical-fatigue models into contextual performance metrics, including without limitation, performance, incident and/or accident-related metrics associated with particular activities and/or with particular environments, such as but not limited to: the number and severity of injuries or cost of repairs associated with a particular incident, increases in insurance premiums, a performance rate, an error rate and/or the like.