Abstract: The present invention provides an event-driven universal neural network circuit. The circuit comprises a plurality of neural modules. Each neural module comprises multiple digital neurons such that each neuron in a neural module has a corresponding neuron in another neural module. An interconnection network comprising a plurality of digital synapses interconnects the neural modules. Each synapse interconnects a first neural module to a second neural module by interconnecting a neuron in the first neural module to a corresponding neuron in the second neural module. Corresponding neurons in the first neural module and the second neural module communicate via the synapses. Each synapse comprises a learning rule associating a neuron in the first neural module with a corresponding neuron in the second neural module. A control module generates signals which define a set of time steps for event-driven operation of the neurons and event communication via the interconnection network.

Abstract: In at least one embodiment, a trust rating system and method provide a precise and accurate, structured (yet adaptable and flexible), quantifying way of expressing historical trustworthiness so the user or decision maker can make more informed decisions on the data or information being evaluated.

Abstract: High value information Alert and Reporting System (HARS) and method to integrate the public into the law enforcement process by providing information on specific wanted persons/persons-of-interest to a diverse range of information display devices specifically selected to display the information to the public. Wanted persons/persons-of-interest are profiled by behavior and acquaintances and predictive behavior algorithms are used to predict locations and venues where there is a higher likelihood the person can be found and then information on that person is provided to the public in that specific area. When the public observes the wanted person, it is reported to HARS, which in turn notifies the proper Law Enforcement Agency (LEA) for investigation and apprehension. Invention can be used for providing public service information to the public in the precise area the information is needed and can also provide commercial advertising information to selected target areas.

Abstract: Utilizing eye tracking to collect naturally expressed affective responses for training an emotional response predictor, comprising: receiving a vote of a user on a segment of content consumed by the user; receiving eye tracking data of the user taken while the user consumed the segment of content; determining, based on the eye tracking data, that a gaze-based attention level to the segment reaches a predetermined threshold; utilizing the vote to generate a label related to an emotional response to the segment; receiving an affective response measurement of the user taken substantially while the user consumed the segment of content; and training a measurement emotional response predictor with the label and the affective response measurement.

Abstract: A system, method and computer program product for validating a document classification process, including a document collection; a document classification process performed on the document collection; a random selection module configured to automatically generate a random validation set of documents from the document collection; and a document review process performed on the random validation set of documents to validate results of the document classification process. The system, method and computer program product are configured to dynamically and in real-time measure and display on a computer display device a best case estimate of a quality of the results of the document classification process based on the documents that are validated, and given a size of a total data set of the document collection.

Abstract: Methods and systems for automating user patterns on a user device are described. A user device receives data representing inputs to a user interface (UI) of the user device and system data associated with each of the inputs, wherein the system data comprises information describing an environment of the user device when the input to the UI was received. The user device then determines that a subset of the inputs to the UI and the system data associated with the subset of the inputs exceeds a threshold probability of matching a pattern of previously-identified UI inputs and system data associated with the previously-identified UI inputs. The user device then executes additional inputs to the UI to complete the matched pattern.

Abstract: A system may be configured to receive performance information regarding a set of network devices; compare the performance information to a set of rule objects; and detect an occurrence of a particular network event. The detecting may include determining that the performance information, associated with a particular network device, of the set of network devices, meets the set of conditions associated with a particular rule object with which the particular network event is associated. The system may further present information regarding the particular rule object, such as information regarding the particular network event, and information regarding a recommendation regarding the particular network event.

Abstract: A method for using hybrid 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, the public data source comprising publicly available healthcare information, the private data source comprising privately managed, company specific healthcare information; 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: A social networking system selects a subset of keywords from a set of master keywords found in user profiles. The method includes selecting a first and second group of user profiles including one or more keywords and computing the number of occurrences of each of the master keywords in the first and second group of profiles. A value may be computed for each of the master keywords based on a comparison of the number of occurrences in the first group of profiles and the number of occurrences in the second group of profiles. The computed value may be used for selecting the subset of keywords from the master keywords and/or ranking the master keywords.

Abstract: This disclosure generally relates to computer-implemented analytics, and more particularly to systems and methods for improved security and precision in executing analytics using SDKs. In one embodiment, an analytics system is disclosed, comprising: a processor; and a memory device operatively connected to the processor and storing processor-executable instructions for: receiving an application programming interface (API) call for a service; parsing the API call to extract an API call name and one or more API call parameters; generating prediction values for one or more interpreted-data parameters; obtaining one or more analytics rules; performing an analytics operation to generate an analytics result according to the one or more analytics rules based on the generated prediction values for the one or more interpreted-data parameters and the extracted one or more API call parameters; and generating a visual representation of the analytics result.

Abstract: Training a machine to provide specialized health care apparatus may include receiving text describing a user's health condition via a user interface. Text may be converted into corresponding medical terms. A database may be searched for a list of health care providers treating health conditions associated with the medical terms. A machine learning model may be built that may include user preference for a predefined set of features associated with the user's health condition and health care provider preference for the predefined set of features in treating the user's health condition. The machine learning model may predict one or more of the health care providers that provide treatment for the user's health condition that matches the user's preference. The machine learning model may be retrained based on one or more of feedback from the user, the health care providers, and updated traits of the users and the health care providers.

Abstract: An adaptive fuzzy rule controlling system for a software defined storage (SDS) system to control performance parameters in a storage node is disclosed. The system includes: a traffic monitoring module, for acquiring observed values of performance parameters in the storage node; an adaptive neural fuzzy inference module, for learning a dynamic relationship between configurations of a plurality of storage devices in the storage node and the performance parameters during a period of time, and outputting fuzzy rules which is built according to the dynamic relationship; a traffic forecasting module, for providing forecasted values of the performance parameters in a particular point in time in the future; and a fuzzy rule control module, for arranging the configuration of the storage devices in the storage node in the particular point in time in the future according to the fuzzy rules and the forecasted values.

Abstract: Implementations of the disclosed subject matter provide methods and systems for using a multistage learner for efficiently boosting large datasets in a machine learning system. A method may include obtaining a first plurality of examples for a machine learning system and selecting a first point in time. Next, a second point in time occurring subsequent to the first point in time may be selected. The machine learning system may be trained using m of the first plurality of examples. Each of the m examples may include a feature initially occurring after the second point in time. In addition, the machine learning system may be trained using n of the first plurality of examples, and each of the n examples may include a feature initially occurring after the first point in time.

Abstract: The present invention relates to a system for improving the flight safety, comprising: a prediction component which predicts behaviors of an aircraft; and an indication component which indicates adjustment of an operation of the aircraft to reduce the possibility of occurrence of abnormal flying behaviors.

Abstract: In a question-answering (QA) environment, a first answer sequence is identified. As identified, the first answer sequence includes a first answer and a second answer. A corpus is analyzed using the first answer and the second answer. Based on the analysis, a set of influence factors corresponding to both the first answer and the second answer are identified. A first answer relationship between the first answer and the second answer is then generated based on the set of influence factors.

Abstract: In a question-answering (QA) environment, a first answer sequence is identified. As identified, the first answer sequence includes a first answer and a second answer. A corpus is analyzed using the first answer and the second answer. Based on the analysis, a set of influence factors corresponding to both the first answer and the second answer are identified. A first answer relationship between the first answer and the second answer is then generated based on the set of influence factors.

Abstract: An approach is provided in which an information handling system analyzes correction information corresponding to an answer generated by a question answer system. The correction information includes a correction to the answer and captured variable information utilized by the question answer system to generate the answer. The information handling system selects input variables based upon the correction analysis and generates a test case that includes the selected input variables and the variable information. In turn, the information handling system tests the question answer system using the generated test case.

Abstract: Systems and techniques are disclosed for training a machine learning model based on one or more regularization penalties associated with one or more features. A template having a lower regularization penalty may be given preference over a template having a higher regularization penalty. A regularization penalty may be determined based on domain knowledge. A restrictive regularization penalty may be assigned to a template based on determining that a template occurrence is below a stability threshold and may be modified if the template occurrence meets or exceeds the stability threshold.

Abstract: An educational course is automatically deconstructed into discrete learning units. Content related to the course that has been stored by an integrated education platform is analyzed, and distinct concepts are extracted from the content. In addition, the learning activities in which users engage while accessing integrated learning services from the platform are recorded. These activities can generally be divided into passive, active, and recall activities. By deconstructing educational courses into individual concepts, a general model of learning is then applied that connects concepts to the activities undertaken by students to learn those concepts. As a result, a model of learning is developed where courses are atomized into individual learning units, each of which comprises a concept and at least one learning activity. The learning units then can be delivered independently or aggregated as desired.

Abstract: Mechanisms are provided, in association with a Question and Answer (QA) system, for implementing corpus identified reasoning when evaluating questions. An input question is received and an answer to the input question and supporting evidence for the answer are determined based on an evaluation of a corpus of information. The supporting evidence is analyzed to identify reasoning criteria specifying a reason as to why the answer is considered to be a correct answer by a provider of the supporting evidence. Rules are generated based on the identified reasoning criteria with the rules correlating the answer with the identified reasoning criteria and features of the input question. The rules are stored as entries in a reasoning data structure a subsequent question is processed based on the reasoning data structure.