Abstract: An apparatus includes a processor component to receive a node device identifier defining an ordering among multiple node devices and among multiple blocks of data distributed among the multiple node devices, and transmit a size of a first subset of the multiple blocks stored within the node device to a control device. In response to receiving instructions to receive a second subset from another node device, perform operations including: receive and store the second subset; group the blocks of data of the first and second subsets into multiple segments in an order that corresponds to the ordering among the multiple blocks, wherein each segment is sized to fit minimum and maximum sizes for transmission to storage device(s); transmit the multiple segments to the storage device(s); and relay multiple segment identifiers from the storage device(s) to the control device in an order corresponding to the ordering among the multiple segments.

Abstract: An apparatus includes a processor to employ a neural network to interpret sketch input to identify an object token that represents a command to display either details of an object or a list of objects on a specified page of a GUI. In response to identifying the object token, the processor is caused to generate GUI instructions to perform the command, and employ the neural network to further interpret the sketch input to identify text specifying a page of the GUI on which to perform the command. In response to identifying the text specifying the page, the processor is caused to incorporate an indication of the page into the GUI instructions, augment a job flow definition with the GUI instructions, and store the job flow definition within a federated area in support of providing the GUI when the job flow of the job flow definition is performed.

Abstract: Systems and methods are provided for performing data mining and statistical learning techniques on a big data set. More specifically, systems and methods are provided for linear regression using safe screening techniques. Techniques may include receiving a plurality of time series included in a prediction hierarchy for performing statistical learning to develop an improved prediction hierarchy. It may include pre-processing data associated with each of the plurality of time series, wherein the pre-processing includes tasks performed in parallel using a grid-enabled computing environment. For each time series, the system may determine a classification for the individual time series, a pattern group for the individual time series, and a level of the prediction hierarchy at which the each individual time series comprises an need output amount greater than a threshold amount.

Abstract: Exemplary embodiments can maximize long-term value in a machine learning system. The system may employ an offline training process and an online training process. In the offline training process, an initial policy is learned to provide a warm start to the online training process. In the online training process, the system applies concurrent reinforcement learning across multiple environments, with the goal of learning efficient policies in real time from in-flight user data in one environment, and applying the learned policies to other environments. With the combination of offline training and online training, the system is able to improve initial performance through the warm start, while adapting to a changing context through concurrent reinforcement learning.

Abstract: One or more embodiments may include techniques to computer generate one or more plots based on computational clustering performed by a system. Embodiments include performing clustering on a dataset to generate a number of clusters of data for the dataset. The clusters may be processed and used to generate the one or more plots. In some embodiments, the plots may include one or more variables plotted against a weighted average score associated with a cluster, the plot may visually indicate the effect that the one or more variables has on the predicted outcome. The one or more plots may be presented in a display on a display device. In some embodiments, the plots may be segmented and each segment may correspond with a number of individual curves. The segmented curves may be plotted and displayed on the display device.

Abstract: An apparatus includes a processor to: assign each value of each set of values of an initial supply meter data and of an initial load meter data to one of multiple buckets based on weather conditions and/or time and date; for each bucket, generate upper and lower bounds of power provision and power consumption values, and use the upper and lower bounds to identify outlier values assigned to the bucket; for each set of values within the initial supply meter data and within the initial load meter data, generate a naive model from the non-outlier values, and use interpolation and the naive model to fill in gaps, thereby generating cleansed supply meter data and cleansed load meter data; and store the cleansed supply meter data and cleansed load meter data together as merged meter data for use in making predictions.

Abstract: Recurrent neural networks (RNNs) can be visualized. For example, a processor can receive vectors indicating values of nodes in a gate of a RNN. The values can result from processing data at the gate during a sequence of time steps. The processor can group the nodes into clusters by applying a clustering method to the values of the nodes. The processor can generate a first graphical element visually indicating how the respective values of the nodes in a cluster changed during the sequence of time steps. The processor can also determine a reference value based on multiple values for multiple nodes in the cluster, and generate a second graphical element visually representing how the respective values of the nodes in the cluster each relate to the reference value. The processor can cause a display to output a graphical user interface having the first graphical element and the second graphical element.

Abstract: A method of determining a false and/or a true positive rate is provided. A true count value and a false count value are initialized for probability bins. For a plurality of records, a truth of event occurrence and a probability of occurrence are read; a probability bin that includes the probability of occurrence is determined; the true count value of the determined probability bin is incremented when the truth of event occurrence indicates true; and the false count value of the determined probability bin is incremented when the truth of event occurrence indicates false. A true positive rate and a false positive rate are computed for each probability bin based on the true count value, the false count value, a determined total number of true event occurrences, and a determined total number of false event occurrences.

Abstract: A system provides image search results based on a query that includes an attribute or an association and a concept identifier. The query is input into a trained query model to define a search syntax for the query. The search syntax is submitted to an expanded annotated image database that includes a concept image of a concept identified by the concept identifier with a plurality of attributes associated with the concept and a plurality of associations associated with the concept. A query result is received based on matching the defined search syntax to one or more of the attributes or one or more of the associations. The query result includes the concept image of the concept associated with the matched one or more of the attributes or one or more of the associations. The concept image included in the received query result is presented in a display.

Abstract: An apparatus includes a processor to: assign a portion of currently available instruction-based processing resources to a first non-neuromorphic performance of an analytical function; in response to availability of sufficient remaining processing resources for a first neuromorphic performance of the analytical function with the same input values, assign a portion of the remaining processing resources to the first neuromorphic performance; analyze the output values generated by the first neuromorphic and non-neuromorphic performances to determine a degree of accuracy of the neural network in performing the analytical function; in response to at least the degree of accuracy exceeding a predetermined threshold, assign a portion of currently available processing resources to a second neuromorphic performance of the analytical function; and in response to availability of sufficient remaining processing resources for a second non-neuromorphic performance of the analytical function, assign a portion of the remaining

Abstract: An apparatus includes a processor component caused to: retrieve metadata of organization of data within a data set, and map data of organization of data blocks within a data file; receive indications of which node devices are available to perform a processing task with a data set portion; and in response to the data set including partitioned data, compare the quantities of available node devices and of the node devices last involved in storing the data set. In response to a match, for each map data map entry: retrieve a hashed identifier for a data sub-block, and a size for each of the data sub-blocks within the corresponding data block; divide the hashed identifier by the quantity of available node devices; compare the modulo value to a designation assigned to each of the available node devices; and provide a pointer to the available node device assigned the matching designation.

Abstract: An apparatus includes a processor to: receive a request to repeat an earlier performance of a first job flow described in a job flow definition; analyze the job flow definition to determine whether the first job flow uses a neural network; in response to a determination that the first job flow uses a neural network, analyze an object associated with the first job flow to determine whether the neural network was trained using training data from a second job flow that does not use a neural network; and in response to a determination that such training data was so used, repeat the earlier performance of the first job flow, perform the second job flow with the same input data values as used in the repeated performance of the first job flow, and analyze corresponding output data values of both performances to determine a degree of accuracy of the neural network.

Abstract: Exemplary embodiments relate to the problem of allocating a finite number of units of a resource among requestors willing to offer different amounts of value for the resource. When different classes of requestors are permitted to cancel the request or fail to show up to collect the unit of the resource with different probabilities (collectively referred to as “wash”), the problem becomes difficult to solve efficiently. According to the procedures described herein, the capacity is artificially inflated to offset the impact of wash, and then protection levels are computed using the inflated capacity as if there was no wash. The capacity is then artificially inflated again based on the new protection levels, and the process is repeated until, e.g., the results converge. Using this procedure, overallocation limits and protection levels can be computed in real-time, and accordingly the resource can be allocated efficiently as new requests are received.

Abstract: A computing device detects an abnormal observation vector using a principal components decomposition. The principal components decomposition includes a sparse noise vector st computed for the observation vector that includes a plurality of values, wherein each value is associated with a variable to define a plurality of variables. The sparse noise vector st has a dimension equal to m a number of the plurality of variables. A zero counter time series value ?t is computed using ?t=?i=1mst[i]. A probability value for ?t is computed using p=?i=?t+1m+1Hc[i]/?i=0m+1Hc[i], where Hc[i] includes a count of a number of times each value of ?t occurred for previous observation vectors. The probability value is compared with a predefined abnormal observation probability value. An abnormal observation indicator is set when the probability value indicates the observation vector is abnormal. The observation vector is output when the probability value indicates the observation vector is abnormal.

Abstract: Various embodiments are generally directed to systems for multi-stage measurement data analysis (MMDA), such as for evaluation and/or validation of data received from a measurement device, for instance. Some embodiments are particularly directed to a MMDA system that utilizes event stream processing (ESP) to provide near real-time validation of measurement data, at least in part, by detecting losses in the measurement data. In many embodiments, the MMDA system may detect technical losses (e.g., due to equipment malfunction) and/or non-technical losses (e.g., due to compromised equipment). For example, the MMDA system may receive measurement data generated by an electrical meter and determine the electrical meter is malfunctioning by detecting a technical loss in the measurement data. In many embodiments, the MMDA system may utilize both direct and indirect measurement data transmitted via separate communication paths to provide near real-time validation of measurement data.

Abstract: An apparatus includes a processor to: perform a testing job flow at least partly within a testing federated area to test a neural network defined by configuration data specifying hyperparameters and trained parameters thereof; and perform a transfer flow to transfer an object indicative of results of the testing from the testing federated area to another federated area, wherein: in response to the degree of accuracy falling below a predetermined minimum threshold, the processor is caused to transfer a specification of the degree of accuracy or a portion of inaccurate output to a training federated area in which the neural network was at least partly trained; and in response to the degree of accuracy exceeding a predetermined maximum threshold, the processor is caused to transfer a copy of the neural network configuration data to a usage federated area in which the neural network is to be made available for use.

Abstract: Exemplary embodiments relate to the problem of determining measurements in a distributed computing environment in which observations relating to the measurements are distributed amongst two or more nodes. Each node, which stores a number of node-specific observations, makes available its observation count and a number of observation sketches. The observations are merged into an array, and the sketches from each node are combined into overall summary sketches representing a summary of the observations across all the nodes. The summary sketches may then be used to approximate the measurement. The described techniques allow for the computation of arbitrary measurements (i.e., measurements that are not predetermined and for whose calculation the environment is not preconfigured) in a grid computing environment with a technical advantage of having very few rounds of data communication (e.g., two or less) required between the nodes in the computing grid.

Abstract: A computing device computes a quantile value. A maximum value and a minimum value are computed for unsorted variable values. An upper bin value and a lower bin value are computed for each bin of a plurality of bins using the maximum and minimum values. A frequency counter is computed for each bin by reading the unsorted variable values a second time. Each frequency counter is a count of the variable values within a respective bin. A bin number and a cumulative rank value are computed for a quantile. The bin number identifies a specific within which a quantile value associated with the quantile is located. The cumulative rank value identifies a cumulative rank for the quantile value associated with the quantile. Frequency data is computed using the frequency counters. The quantile value is computed using the frequency data and the cumulative rank value for the quantile and output.

Abstract: A computing device predicts occurrence of an event or classifies an object using distributed unlabeled data. Supervised data that includes a labeled subset of a plurality of observation vectors is identified. A total number of threads that will perform labeling of an unlabeled subset of the plurality of observation vectors is determined. The identified supervised data is uploaded to each thread of the total number of threads. Unlabeled observation vectors are randomly select from the unlabeled subset of the plurality of observation vectors to allocate to each thread of the total number of threads. The randomly selected, unlabeled observation vectors are uploaded to each thread of the total number of threads based on the allocation. The value of the target variable for each observation vector of the unlabeled subset of the plurality of observation vectors is determined based on a converged classification matrix and output to a labeled dataset.

Abstract: One or more embodiments may include techniques to computer generate one or more plots based on computational clustering performed by a system. Embodiments include performing clustering on a dataset to generate a number of clusters of data for the dataset. The clusters may be processed and used to generate the one or more plots. In some embodiments, the plots may include one or more variables plotted against a weighted average score associated with a cluster, the plot may visually indicate the effect that the one or more variables has on the predicted outcome. The one or more plots may be presented in a display on a display device. In some embodiments, the plots may be segmented and each segment may correspond with a number of individual curves. The segmented curves may be plotted and displayed on the display device.