Abstract: Embodiments of the present invention provide an artificial neural network system for improved machine learning, feature pattern extraction and output labeling. The system comprises a first spiking neural network and a second spiking neural network. The first spiking neural network is configured to spontaneously learn complex, temporally overlapping features arising in an input pattern stream. Competitive learning is implemented as Spike Timing Dependent Plasticity with lateral inhibition in the first spiking neural network. The second spiking neural network is connected with the first spiking neural network through dynamic synapses, and is trained to interpret and label the output data of the first spiking neural network. Additionally, the output of the second spiking neural network is transmitted to a computing device, such as a CPU for post processing.

Abstract: A machine learning computing system for predicting a probability of success of an identified computing device error condition may include at least a first data repository storing a plurality of historic data records corresponding to one or more computing device error conditions and a second data repository storing a plurality of solutions to each of the computing device error conditions stored in the first data repository. A server is configured to receive a computing device error message from at least one computing center device and analyze the computing device error message to identify an associated error condition category. The server identifies at least two solutions to an associated error condition and predict a probability of success for each of the at least two solutions. The server then initiates at least one solution that has a greatest probability of success and updates the second data repository.

Abstract: A characteristic value estimation device has a sensor data input unit to input sensor data detected by one or more sensors, a model input unit to input a first calculation model, a model learning unit to perform learning on a second calculation model, a model switch to select any one of the first calculation model and the second calculation model, a predictive value calculation unit to calculate an error of the calculation model, a probability distribution correction unit to correct the probability distribution of the uncertain parameter, a virtual sensor value estimation unit to estimate sensor data of a virtual sensor arranged virtually, a characteristic value distribution estimation unit to estimate a detailed distribution of the characteristic value, the sensor data of the virtual sensor, and the sensor data of the sensor, and a reliability calculation unit to calculate a reliability of the precise characteristic value distribution.

Abstract: A computer implemented method includes accessing narrative data, the narrative data comprising a sequence of words arranged in sentence patterns. The method parses each sentence in a sentence pattern which includes a verb matching a functional type to extract sentence subjects and objects to an event template. The method then stores events in an event data store, each event including sentence data mapped to the event template to create an event record. The method further includes mapping event records to a story rule, each story rule including at least one actor and an action associated with the actor, and the mapping includes storing a story record including the event records organized by time. An output of an analysis of the story record occurs, where the analysis is based on a list of transgression actions and retribution actions, and balances the transgression actions and the retribution actions.

Abstract: One or more failure regions are determined for an electrical device by training a machine learning classifier, including analyzing data points for the device and recognizing patterns in the data points. Each data point indicates pass or fail of the device for a particular combination of factors relating to the operation of the device. The trained machine learning classifier is used to predict the pass/fail state of new data points for the electrical device. Each new data point corresponds to a new combination of the factors relating to the operation of the device not previously analyzed by the machine learning classifier. A pass/fail border region can be identified for the electrical device based on the training of the machine learning classifier, the pass/fail border region excluding data points for which the electrical device is expected to pass or fail with a high degree of certainty.

Abstract: The present disclosure provides an emoji recommendation method and device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for modifying a computational graph to include send and receive nodes. Communication between unique devices performing operations of different subgraphs of the computational graph can be handled efficiently by inserting send and receive nodes into each subgraph. When executed, the operations that these send and receive nodes represent may enable pairs of unique devices to conduct communication with each other in a self-sufficient manner. This shifts the burden of coordinating communication away from the backend, which affords the system that processes this computational graph representation the opportunity to perform one or more other processes while devices are executing subgraphs.

Abstract: An example embodiment may involve a machine learning model representing relationships between a dependent variable and a plurality of n independent variables. The dependent variable may be a function of the n independent variables, where the n independent variables are measurable characteristics of computing devices, and where the dependent variable is a predicted behavior of the computing devices. The embodiment may also involve obtaining a target value of the dependent variable, and separating the n independent variables into n?1 independent variables with fixed values and a particular independent variable with an unfixed value. The embodiment may also involve performing a partial inversion of the function to produce a value of the particular independent variable such that, when the function is applied to the value of the particular independent variable and the n?1 independent variables with fixed values, the dependent variable is within a pre-defined range of the target value.

Abstract: A property vector representing extractable measurable properties, such as musical properties, of a file is mapped to semantic properties for the file. This is achieved by using artificial neural networks “ANNs” in which weights and biases are trained to align a distance dissimilarity measure in property space for pairwise comparative files back towards a corresponding semantic distance dissimilarity measure in semantic space for those same files. The result is that, once optimised, the ANNs can process any file, parsed with those properties, to identify other files sharing common traits reflective of emotional-perception, thereby rendering a more liable and true-to-life result of similarity/dissimilarity. This contrasts with simply training a neural network to consider extractable measurable properties that, in isolation, do not provide a reliable contextual relationship into the real-world.

Abstract: Systems and methods for performing a quantization of artificial neural networks (ANNs) are provided. An example method may include receiving a description of an ANN and input data associated with the ANN, wherein the input data are represented according to a first data type; selecting a first value interval of the first data type to be mapped to a second value interval of a second data type; performing, based on the input data and the description of the ANN, the computations of one or more neurons of the ANN, wherein the computations are performed for at least one value within the second value interval, the value being a result of mapping a value of the first value interval to a value of the second value interval; determining, a measure of saturations in neurons of the ANN, and adjusting, based on the measure of saturations, the value intervals.

Abstract: Techniques for using different data sources for a predictive model are described. According to various implementations, techniques described herein enable different data sets to be used to generate a predictive model, while minimizing the risk that individual data points of the data sets will be exposed by the predictive model. This aids in protecting individual privacy (e.g., protecting personally identifying information for individuals), while enabling robust predictive models to be generated using data sets from a variety of different sources.

Abstract: A computer-implemented method and computer processing system are provided for update management for a neural network. The method includes performing an isotropic update process on the neural network using a Resistive Processing Unit. The isotropic update process uses a multiplicand and a multiplier from a multiplication operation. The performing step includes scaling the multiplicand and the multiplier to have a same order of magnitude.

Abstract: Described herein is a system that transmits and combines local models, that individually comprise a set of local parameters computed via stochastic gradient descent (SGD), into a global model that comprises a set of global model parameters. The local models are computed in parallel at different geographic locations along with symbolic representations. The symbolic representations can be used to combine the local models. The global model can determine a likelihood, given a new data instance of a feature set, that a user performs a computer interaction with the content element. For instance, the system can use the model to provide search results in response to a search query submitted by a user. Or, the system can use the model to make a recommendation or suggestion to a user in response to a request for content (e.g., display a targeted advertisement, suggest a news story, etc.).

Abstract: A computer-implemented method executed by a processor for training a neural network to recognize driving scenes from sensor data received from vehicle radar is presented. The computer-implemented method includes extracting substructures from the sensor data received from the vehicle radar to define a graph having a plurality of nodes and a plurality of edges, constructing a neural network for each extracted substructure, combining the outputs of each of the constructed neural networks for each of the plurality of edges into a single vector describing a driving scene of a vehicle, and classifying the single vector into a set of one or more dangerous situations involving the vehicle.

Abstract: A classification apparatus includes: a calculation unit that outputs, as a classification result, results of classification by each of a plurality of classifiers with respect to learning data formed of data of at least two classes at a learning time and calculates a combination result value obtained by linear combination, using a combination coefficient, of results of classification by each of the plurality of classifiers with respect to the learning data to output the calculated combination result value as the classification result at a classification time; an extraction unit that extracts a correct solution class and an incorrect solution class for each of the classifiers from the classification result; a difference calculation unit that calculates a difference between the correct solution class and the incorrect solution class for each of the classifiers; a conversion unit that calculates a feature vector using the calculated difference for each of the classifiers; and a combination coefficient setting uni

Abstract: A system and method as disclosed herein develops a predicted current remaining useful life (RUL) of a component through a generalized fault and usage model that is designed through a process of simplifying Paris' Law (or other power law) in conjunction with a Kalman Smoother (or other filtering technique). One of the many advantages of this state observer technique is that the backward/forward filtering technique employed by the Kalman Smoother has no phase delay, which allows for the development of a generalized, zero tuning model that provides an improved component health trend, and therefore a better estimate of the predicted current RUL.

Abstract: Approaches for classifying training samples with minimal error in a neural network using a low complexity neural network classifier, are described. In one example, for the neural network, an upper bound on the Vapnik-Chervonenkis (VC) dimension is determined. Thereafter, an empirical error function corresponding to the neural network is determined. A modified error function based on the upper bound on the VC dimension and the empirical error function is generated, and used for training the neural network.

Abstract: The content of a knowledge datastore is evaluated and improved. In a first aspect, the content effectiveness of individual snippets is evaluated and a content creator is requested to improve snippets with a low content effectiveness. In a second aspect, the supply of and demand for content in each content topic is evaluated, and a content creator is requested to create articles for content topics for which the demand exceeds the supply. In a third aspect, the message responsiveness and content effectiveness of content topics is evaluated and a content creator is requested to create articles for content topics with a low message responsiveness and/or content effectiveness. In a fourth aspect, the content utilization and content effectiveness of individual snippets is monitored and snippets with a high content effectiveness and a low content utilization are promoted, whereas snippets with a low content effectiveness and a low content utilization are deprecated.

Abstract: Aspects of the subject disclosure may include, for example, embodiments provisioning a neural network comprising a plurality of layers. Further embodiments include provisioning a plurality of Markov logic state machines among the plurality of layers of the neural network resulting in a machine learning application. Additional embodiments include training the machine learning application using historical network video traffic resulting in a trained machine learning application. Also, embodiments include receiving current network video traffic. Embodiments include provisioning network resources to route the current network video traffic according to the trained machine learning application. Other embodiments are disclosed.

Abstract: A method for ingesting a plurality of content according to a statistical similarity of at least one portion of the ingested plurality of content into an information handling system capable of answering questions, whereby the ingested plurality of content is based on a received topic and ingesting the plurality of content comprises ingesting a plurality of documents associated with the received topic is provided. The method may include determining at least one similarity between each document based on a similarity criteria. The method may also include applying a statistical model to characterize the determined at least one similarity between each document. The method may further include creating at least one pair-wise link for each document. The method may additionally include mapping the created at least one pair-wise link. The method may include generating a plurality of rules for ingesting a plurality of additional content.