Abstract: A “Predictive Controller” operates with any type of controller or user input device to predict user inputs or responses to a current state of an application. A predictive model of the current state of the application is applied to prior user inputs to jointly predict a current user-specific psychological state or profile of the user and a predicted next user response or input. The predicted response or input is provided as the user input to the particular application prior to receiving the actual user input, thereby reducing latency of the response of the application to that actual user input. In addition, a tangible feedback corresponding to the predicted next user input is provided. Further, the predictive capabilities of the Predictive Controller can be applied to locally or remotely hosted instances of the application to reduce latencies associated with user inputs received from any type of controller or user input device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a sequence generation neural network. One of the methods includes obtaining a batch of training examples; for each of the training examples: processing the training network input in the training example using the neural network to generate an output sequence; for each particular output position in the output sequence: identifying a prefix that includes the system outputs at positions before the particular output position in the output sequence, for each possible system output in the vocabulary, determining a highest quality score that can be assigned to any candidate output sequence that includes the prefix followed by the possible system output, and determining an update to the current values of the network parameters that increases a likelihood that the neural network generates a system output at the position that has a high quality score.

Abstract: A method, system, and computer program product for learning a recognition model for recognition processing. The method includes preparing one or more examples for learning, each of which includes an input segment, an additional segment adjacent to the input segment and an assigned label. The input segment and the additional segment are extracted from an original training data. A classification model is trained, using the input segment and the additional segment in the examples, to initialize parameters of the classification model so that extended segments including the input segment and the additional segment are reconstructed from the input segment. Then, the classification model is tuned to predict a target label, using the input segment and the assigned label in the examples, based on the initialized parameters. At least a portion of the obtained classification model is included in the recognition model.

Abstract: A mechanism is provided in a data processing system for tailoring question answering system output based on user expertise. The mechanism receives an input question from a questioning user and determines a set of features associated with text of the input question. The mechanism determines an expertise level of the questioning user based on the set of features associated with the text of the input question using a trained expertise model. The mechanism generates one or more candidate answers for the input question and tailors output of the one or more candidate answers based on the expertise level of the questioning user.

Abstract: A method for receiving a plurality of types of data within a cognitive information processing system environment comprising: receiving data from a plurality of data sources, the plurality of data sources comprising a public data source and a private data source; accessing information from the plurality of data sources via a cognitive data management module; and, providing the information to an inference and learning system.

Abstract: The prediction function creation device according to the present invention for creating a prediction function to derive an objective variable by using a set of samples that include explanatory variables and an objective variable, the device includes: a clustering unit that clusters the respective samples by giving labels, and assigns weights to each label in accordance with patterns of missing values for the explanatory variables in labeled samples; a child model creation unit that makes portions of the training data partial training data on the basis of the weights, and determines an explanatory variable that constitutes the prediction function on the basis of patterns of missing values for the explanatory variables in the samples; and a mixture model creation unit that creates the prediction function with respect to each pattern of missing values by using the explanatory variable and the determined partial training data.

Abstract: The present invention relates to a probabilistic programming compiler that (a) generates data-parallel inference code to sample from probability distributions in models provided to the compiler; and (b) utilizes a modular framework to allow addition and removal of inference algorithm information based on which the compiler generates the inference code. For a given model, the described compiler can generate inference code that implements any one or more of the inference algorithms that are available to the compiler. The modular compiler framework utilizes an intermediate representation (IR) that symbolically represents features of probability distributions. The compiler then uses the IR as a basis for emitting inference code to sample from the one or more probability distributions represented in the IR.

Abstract: The present disclosure describes a system and method for improving the way computing devices execute genetic algorithms. A fuzzy logic controller takes various properties of the genetic algorithm (such as the diversity of the population, the performance history of the algorithm in terms of time-efficiency and/or effectiveness at improving the best fitness function results, and available computing resources) to dynamically manage the parameters of the genetic algorithm. In some embodiments, the fuzzy inference system that provides parameters to the genetic algorithm is itself controlled by another fuzzy inference system.

Abstract: A system and computer implemented method for generating a set of inferred questions for a question answering system is disclosed. The method may include determining, based on context data, a user state. The method may also include extracting characterization information for an object satisfying an attention criteria. The characterization information may be configured to include sensory data. The method may also include determining a relationship between the object and the user state based on the characterization information for the object and the context data of the user state. The method may also include generating, based on the relationship between the object and the user state, a set of inferred questions for a question answering system.

Abstract: A data architecture for use within a cognitive information processing system environment comprising: a plurality of data sources, the plurality of data sources comprising a public data source and a private data source; and, a cognitive data management module, the cognitive data management module accessing information from the plurality of data sources and providing the information to an inference and learning system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using recurrent neural networks to analyze health events. One of the methods includes: processing each of a plurality of initial temporal sequences of health events to generate, for each of the initial temporal sequences, a respective network internal state of a recurrent neural network for each time step in the initial temporal sequence; storing, for each of the initial temporal sequences, one or more of the network internal states for the time steps in the temporal sequence in a repository; obtaining a first temporal sequence; processing the first temporal sequence using the recurrent neural network to generate a sequence internal state for the first temporal sequence; and selecting one or more initial temporal sequences that are likely to include health events that are predictive of future health events in the first temporal sequence.

Abstract: A method for relative temperature preference learning is described. In one embodiment, the method includes identifying one or more current settings of a thermostat located at a premises, identifying one or more current indoor and outdoor conditions, calculating a current indoor differential between the current indoor temperature and the current target temperature, calculating a current outdoor differential between the current outdoor temperature and the current target temperature, and learning temperature preferences based on an analysis of the one or more current indoor conditions and the one or more current outdoor conditions. The one or more current settings of the thermostat include at least one of a current target temperature, current runtime settings, and current airflow settings.

Abstract: A mechanism is provided in a data processing system for tailoring question answering system output based on user expertise. The mechanism receives an input question from a questioning user and determines a set of features associated with text of the input question. The mechanism determines an expertise level of the questioning user based on the set of features associated with the text of the input question using a trained expertise model. The mechanism generates one or more candidate answers for the input question and tailors output of the one or more candidate answers based on the expertise level of the questioning user.

Abstract: Multiple processors share access, via a bus, to a pipelined NFA engine. The NFA engine can implement an NFA of the type that is not a DFA (namely, it can be in multiple states at the same time). One of the processors communicates a configuration command, a go command, and an event generate command across the bus to the NFA engine. The event generate command includes a reference value. The configuration command causes the NFA engine to be configured. The go command causes the configured NFA engine to perform a particular NFA operation. Upon completion of the NFA operation, the event generate command causes the reference value to be returned back across the bus to the processor.

Abstract: Systems and methods for content selection with first and second recommendation engines are disclosed herein. The system can include a memory include a content library database and a model database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include one or more servers that can include a packet selection system and a presentation system. These one or more servers can: receive response data from the user device; provide received response data to a first recommendation engine; alert a second recommendation engine when a selected next node is a placeholder node; retrieve at least one statistical model relevant to selection of next node content; and select next node content based on an output of the at least one statistical model.

Abstract: A method for receiving a plurality of types of data within a cognitive information processing system environment comprising: receiving data from a plurality of data sources, the plurality of data sources comprising a public data source and a private data source; accessing information from the plurality of data sources via a cognitive data management module; and, providing the information to an inference and learning system.

Abstract: The field of the disclosure relates generally to a method and system for analyzing behavior of a computer infrastructure and the displaying the behavior of the computer infrastructure in a graphical manner. The system comprises an analytical engine connected to agents running on devices in the computer infrastructure and analyzing continuous data and asynchronous data.

Abstract: Techniques for use in connection with performing optimization using an objective function. The techniques include using at least one computer hardware processor to perform: beginning evaluation of the objective function at a first point; before evaluating the objective function at the first point is completed: identifying, based on likelihoods of potential outcomes of evaluating the objective function at the first point, a second point different from the first point at which to evaluate the objective function; and beginning evaluation of the objective function at the second point.

Abstract: The invention concerns a method to compare two data obtained from a sensor or interface, carried out by processing means of a processing unit, the method comprising the computing of a similarity function between two feature vectors of the data to be compared, characterized in that each feature vector of a datum is modelled as the summation of Gaussian variables, said variables comprising: a mean of a class to which the vector belongs, an intrinsic deviation, and an observation noise of the vector, each feature vector being associated with a quality vector comprising information on the observation noise of the feature vector, and in that the similarity function is computed from the feature vectors and associated quality vectors.

Abstract: Systems and methods for content selection with first and second recommendation engines are disclosed herein. The system can include a memory include a content library database and a model database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include one or more servers that can include a packet selection system and a presentation system. These one or more servers can: receive response data from the user device; provide received response data to a first recommendation engine; alert a second recommendation engine when a selected next node is a placeholder node; retrieve at least one statistical model relevant to selection of next node content; and select next node content based on an output of the at least one statistical model.