Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the methods includes providing an output derived from a first portion of a neural network output as a system output; determining one or more sets of writing weights for each of a plurality of locations in an external memory; writing data defined by a third portion of the neural network output to the external memory in accordance with the sets of writing weights; determining one or more sets of reading weights for each of the plurality of locations in the external memory from a fourth portion of the neural network output; reading data from the external memory in accordance with the sets of reading weights; and combining the data read from the external memory with a next system input to generate the next neural network input.

Abstract: A method for determining a drill event includes receiving a set of historic drill reports with annotations. The historic drill reports include a plurality of entries including multiple acronyms relating to a single drilling factor. A set of entries of the plurality of entries indicates an associated depth. The method further includes training a report analysis engine utilizing the historic drill reports and annotations; receiving a drill report associated with a well; and determining a drill event and associated depth utilizing the report analysis engine applied to the drill report.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for improving operational efficiency within a data center by modeling data center performance and predicting power usage efficiency. An example method receives a state input characterizing a current state of a data center. For each data center setting slate, the state input and the data center setting slate are processed through an ensemble of machine learning models. Each machine learning model is configured to receive and process the state input and the data center setting slate to generate an efficiency score that characterizes a predicted resource efficiency of the data center if the data center settings defined by the data center setting slate are adopted t. The method selects, based on the efficiency scores for the data center setting slates, new values for the data center settings.

Abstract: Described is a system for proactive and reactive cognitive control using a neural module. The system calculates, for each hypothesis of a set of hypotheses, a probability that an event will occur. The neural module comprises a plurality of neurons and includes the PC module, a prefrontal cortex (PFC) module, an anterior cingulate cortex (ACC) module, a locus coeruleus (LC) module, and a basal forebrain (BF) module. The set of hypotheses are related to tasks to be performed by a plurality of groups, each group having a corresponding hypothesis. For each probability, the system calculates a conflict value across all hypotheses with the ACC module, compares each conflict value to a predetermined threshold using the BF and LC modules. A determination is made whether to directly output the calculated probability or perform an additional probability calculation and output an updated probability.

Abstract: A method for condition monitoring of distributed drive-trains using Bayesian data fusion approach for measured data includes measurement of physical signals obtained from sensors attached to the components being chosen from the drive-train which are delivered to the computer means for processing the measured data and performing data fusion processes, using a data from information database containing at least one information system. The method is characterized by comprising two stages for data fusion processes performed by using Bayesian Inference, the first one for local data fusion process and the second one for global data fusion process, and on the basis of the second stage the assessment process of the condition of the drive-train is performed by choosing the maximum value of the received data, which maximum value serves as an indicator for the most likely fault present in the drive-train.

Abstract: Systems and methods associated with neural network verification are disclosed. One example method may be embodied on a non-transitory computer-readable medium storing computer-executable instructions. The instructions, when executed by a computer, may cause the computer to train a neural network with a training data set to perform a predefined task. The instructions may also cause the computer to train the neural network with a sentinel data set. The sentinel data set may cause the neural network to provide an identification signal in response to a predefined query set. The instructions may also cause the computer to verify whether a suspicious service operates an unauthorized copy of the neural network. The suspicious service may be verified by extracting the identification signal from responses the suspicious service provides to the predefined query set.

Abstract: A semantic engine including a group of functions or sub-engines configured to operate together to provide a complete analysis and understanding of digital information in order to provide results or subsequent actions. The semantic engine provide a set of algorithms, including a Naïve Bayes (Bayesian) algorithm, intelligent, self-learning semantic understanding algorithm, lexical analysis algorithm, word trimming algorithm, part-of-speech (POS) tagging algorithm, and textual inference algorithm.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for an adaptive oracle-trained learning framework for automatically building and maintaining models that are developed using machine learning algorithms. In embodiments, the framework leverages at least one oracle (e.g., a crowd) for automatic generation of high-quality training data to use in deriving a model. Once a model is trained, the framework monitors the performance of the model and, in embodiments, leverages active learning and the oracle to generate feedback about the changing data for modifying training data sets while maintaining data quality to enable incremental adaptation of the model.

Abstract: Methods, systems, and computer program products for detection of an arbitrarily-shaped source of an abnormal event via use of a hierarchical reconstruction method are provided herein. A computer-implemented method includes detecting an abnormal event based on analysis of sensor data, wherein said analysis of the sensor data comprises comparing the sensor data to a user-defined threshold; generating a query based on the detected abnormal event; processing the query against one or more given data repositories; executing an inverse model using an output generated in relation to said processing to identify a source of the detected abnormal event, wherein the source comprises an arbitrary shape; and outputting the identified source of the detected abnormal event.

Abstract: A parameter-based multi-model blending method and system are described. The method includes selecting a parameter of interest among parameters estimated by each of a set of individual models, running the set of individual models with a range of inputs to obtain a range of estimates of the parameters from each of the set of individual models, and identifying, for each of the set of individual models, critical parameters among the parameters estimated, the critical parameters exhibiting a specified correlation with an error in estimation of the parameter of interest. For each subspace of combinations of the critical parameters, obtaining a parameter-based blended model is based on blending the set of individual models in accordance with the subspace of the critical parameters, the subspace defining a sub-range for each of the critical parameters.

Abstract: A parameter-based multi-model blending method and system are described. The method includes selecting a parameter of interest among parameters estimated by each of a set of individual models, running the set of individual models with a range of inputs to obtain a range of estimates of the parameters from each of the set of individual models, and identifying, for each of the set of individual models, critical parameters among the parameters estimated, the critical parameters exhibiting a specified correlation with an error in estimation of the parameter of interest. For each subspace of combinations of the critical parameters, obtaining a parameter-based blended model is based on blending the set of individual models in accordance with the subspace of the critical parameters, the subspace defining a sub-range for each of the critical parameters.

Abstract: A parameter-based multi-model blending method and system are described. The method includes selecting a parameter of interest among parameters estimated by each of a set of individual models, running the set of individual models with a range of inputs to obtain a range of estimates of the parameters from each of the set of individual models, and identifying, for each of the set of individual models, critical parameters among the parameters estimated, the critical parameters exhibiting a specified correlation with an error in estimation of the parameter of interest. For each subspace of combinations of the critical parameters, obtaining a parameter-based blended model is based on blending the set of individual models in accordance with the subspace of the critical parameters, the subspace defining a sub-range for each of the critical parameters.

Abstract: Methods and a system are provided. A method includes optimizing, by a natural language processing based response optimizer having a processor, responses in an online question and answer session using natural language processing. The optimizing step includes deriving a candidate answer to a question posed in natural language and gathering support for the candidate answer by accessing a social network. The support is weighted by at least one of degree centrality, betweenness centrality, closeness centrality, Eigenvalue, hub, and authority of nodes in the social network that are associated with the support.

Abstract: A calculation formula learning unit sets a coefficient relating to a time lag element in a thermal displacement estimation calculation formula by machine learning while fixing a coefficient relating to measured data except the coefficient relating to the time lag element at a predetermined value based on a difference between a thermal displacement estimated value about a machine element calculated by substituting a measured data group into the thermal displacement estimation calculation formula and a thermal displacement actual measured value about the machine element; sets the coefficient relating to the measured data except the coefficient relating to the time lag element in the thermal displacement estimation calculation formula by machine learning based on the difference while fixing the coefficient relating to the time lag element at a predetermined value; and repeats the machine learning.

Abstract: Methods, computer program products, and systems are presented. The methods computer program products, and systems can include, for instance: determining an insertion interval of a row for insertion into a decision table; and guiding insertion of the row for insertion into the decision table based on a result of the determining.

Abstract: Methods and a system are provided. A method includes optimizing, by a natural language processing based response optimizer having a processor, responses in an online question and answer session using natural language processing. The optimizing step includes deriving a candidate answer to a question posed in natural language and gathering support for the candidate answer by accessing a social network. The support is weighted by at least one of degree centrality, betweenness centrality, closeness centrality, Eigenvalue, hub, and authority of nodes in the social network that are associated with the support.

Abstract: A computer system and computer-implemented techniques for determining crop harvest times during a growing season based upon hybrid seed properties, weather conditions, and geo-location of planted fields is provided. In an embodiment, determining crop harvest times for corn fields may be accomplished using a server computer system that receives over a digital communication network, electronic digital data representing hybrid seed properties, including seed type and relative maturity, and weather data for the specific geo-location of the agricultural field.

Abstract: Provided are a neuromorphic computing device, memory device, system, and method to maintain a spike history for neurons in a spiking neural network. A neural network spike history is generated in a memory device having an array of rows and columns of memory cells. There is one row of the rows for each of a plurality of neurons and columns for each of a plurality of time slots. Indication is made in a current column in the row of the memory cells for a firing neuron that a spike was fired. Indication is made in the current column in rows of memory cells of idle neurons that did not fire that a spike was not fired. Information in the array is used to determine a timing difference between a connected neuron and the firing neuron and to adjust a weight of the connecting synapse.

Abstract: The described technology can provide semantic translations of a selected language snippet. This can be accomplished by mapping snippets for output languages into a vector space; creating predicates that can map new snippets into that vector space; and, when a new snippet is received, generating and matching a vector representing that new snippet to the closest vector for a snippet of a desired output language, which is used as the translation of the new snippet. The procedure for mapping new snippets into the vector space can include creating a dependency structure for the new snippet and computing a vector for each dependency structure node. The vector computed for the root node of the dependency structure is the vector representing the new snippet. A similar process is used to train a transformation function for each possible node type, using language snippets already associated with a dependency structure and corresponding vectors.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes generating, by a speech recognition system, a matrix from a predetermined quantity of vectors that each represent input for a layer of a neural network, generating a plurality of sub-matrices from the matrix, using, for each of the sub-matrices, the respective sub-matrix as input to a node in the layer of the neural network to determine whether an utterance encoded in an audio signal comprises a keyword for which the neural network is trained.