Abstract: In an approach for compressing a neural network, a processor receives a neural network, wherein the neural network has been trained on a set of training data. A processor receives a compression ratio. A processor compresses the neural network based on the compression ratio using an optimization model to solve for sparse weights. A processor re-trains the compressed neural network with the sparse weights. A processor outputs the re-trained neural network.

Abstract: Context-awareness in preventative maintenance is provided by receiving sensor data from a plurality of monitored systems; extracting a first plurality of features from a set of work orders for the monitored systems, wherein individual work orders include a root cause analysis for a context in which a nonconformance in an indicated monitored system occurred; predicting, via a machine learning model, a nonconformance likelihood for each monitored system based on the first plurality of features; selecting a subset of alerts based on predicted nonconformance likelihoods for the monitored systems; in response to receiving a user selection from the first set of alerts and a reason for the user selection, recording the reason as a modifier for the machine learning model; and updating the machine learning model to predict the subsequent nonconformance likelihoods using a second plurality of features that excludes the additional feature identified from the first plurality of features.

Abstract: In an approach to improve detecting and identifying objects through orbital synthetic aperture radar satellites, embodiments arrange an array of elements in a predetermined configuration, and process, by a threshold and signature analysis, detected peaks in processed image data. Further, embodiments generate a list of objects detections based on the processed peaks, and identify an object based on amplitude, polarization ration, and polarization phase difference. Additionally, embodiments, classify the identified object based on the generated list of objects, and output, by a user interface, a list of probable object detections with position coordinates and identifications based on the classified identified objects, wherein the list of probable objects are above or within a predetermine threshold of confidence.

Abstract: In unsupervised interpretable machine learning, one or more datasets having multiple features can be received. A machine can be trained to jointly cluster and interpret resulting clusters of the dataset by at least jointly clustering the dataset into clusters and generating hyperplanes in a multi-dimensional feature space of the dataset, where the hyperplanes separate pairs of the clusters, where a hyperplane separates a pair of clusters. Jointly clustering the dataset into clusters and generating hyperplanes can repeat until convergence, where the clustering in a subsequent iteration uses the generated hyperplanes from a previous iteration to optimize performance of the clustering. The hyperplanes can be adjusted to further improve the performance of the clustering. The clusters and interpretation of the clusters can be provided, where a cluster's interpretation is provided based on hyperplanes that construct a polytope containing the cluster.

Abstract: A method includes: receiving, by a computing device, data from sensors in a manufacturing environment; mapping, by the computing device, the data into a deep learning network; learning, by the computing device, correlations between inputs and outputs of the manufacturing environment using the data; pruning, by the computing device, the deep learning network; predicting, by the computing device and using the pruned network, an output of the pruned network from the inputs of the manufacturing environment; linearizing, by the computing device, the pruned network; optimizing, by the computing device, the output of the linearized pruned network to calculate predicted inputs for the manufacturing environment; and changing, by the computing device, operation inputs in the manufacturing environment to match the predicted inputs.

Abstract: An approach to federated learning of a machine learning model may be provided. The approach may include broadcasting hyperparameters of a machine learning model to one or more client computing devices from a primary device associated with an outer loop or an inner loop. A gradient for the loss function may be calculated at the client device if previous gradients have been sufficiently large. If gradients exceeds a threshold, the client can send the mini-batch of gradients or the difference of the mini-batch of gradients back to the primary device. A search direction may be calculated based on the full gradient of the loss function for an outer loop or the mini-batch of gradient differences for an inner loop. A learning rate step may be calculated from the search direction. The hyperparameter may be updated for the inner loop based on the learning rate.

Abstract: A system and a method of managing a manufacturing process includes receiving production data relating to the manufacturing process and determining an operational mode associated with the manufacturing process using historical, multivariate senor data. The method may further determine a recommended action to affect production based on the determined operational mode. The operational mode may be based on at least one of: a level of operation in a continuous flow process relating to a joint set of process variables, a representation of a joint dynamic of the set of process variables over a predefined length, and a joint configuration of an uptime/downtime of a plurality of units comprising a process flow.

Abstract: A computer implemented method of generating a classifier engine for machine learning includes receiving a set of data points. A semi-supervised k-means process is applied to the set of data points from each class. The set of data points in a class is clustered into multiple clusters of data points, using the semi-supervised k-means process. Multi-polytopes are constructed for one or more of the clusters from all classes. A support vector machine (SVM) process is run on every pair of clusters from all classes. Separation hyperplanes are determined for the clustered classes. Labels are determined for each cluster based on the separation by hyperplanes.

Abstract: A sub-process sequence is identified from a temporal dataset. Based on time information, predictors are categorized as being available or not available during time periods. The predictors are used to make predictions of quantities that will occur in a future time period. The predictors are grouped into groups of a sequence of sub-processes, each including a grouping of one or more of the predictors. Information is output that allows a human being to modify the groups. The groups are finalized, responsive to any modifications. Prediction models are extracted based on dependencies between groups and sub-processes. A final predication model is determined based on a prediction model from the prediction models that best meets criteria. A dependency graph is generated based on the final prediction model. Information is output to display the final dependency graph for use by a user to adjust or not adjust elements of the sequential process.

Abstract: A computer implemented method of preparing process data for use in an artificial intelligence (AI) model includes collecting and storing raw data as episodic data for each episode of a process. An episode data generator assigns an episode identifier each set of episodic data. The raw data per episode is transformed into a standardized episodic data format that is usable by the AI model. Metrics are assigned to the episodic data and the episodic data is aggregated in an episode store. The data in the episode store is used by a feature extraction and learning module to extract and rank features.

Abstract: In various embodiments, a computing device, a non-transitory storage medium, and a computer implemented method of improving a computational efficiency of a computing platform in processing a time series data includes receiving the time series data and grouping it into a hierarchy of partitions of related time series. The hierarchy has different partition levels. A computation capability of a computing platform is determined. A partition level, from the different partition levels, is selected based on the determined computation capability. One or more modeling tasks are defined, each modeling task including a group of time series of the plurality of time series, based on the selected partition level. One or more modeling tasks are executed in parallel on the computing platform by, for each modeling task, training a model using all the time series in the group of time series of the corresponding modeling task.

Abstract: A computer implemented method includes generating a pipeline graph having a plurality of layers, each of the plurality of layers having one or more machine learning components for performing a predictive modeling task. A plurality of pipelines are operated through the pipeline graph on a training dataset to determine a respective plurality of results. Each of the plurality of pipelines are distinct paths through selected ones of the one or more machine learning components at each of the plurality of layers. The plurality of results are compared to known results based on a user-defined metric to output one or more leader pipelines.

Abstract: A method for automatically constructing and organizing a navigation graph includes receiving input data including a plurality of reports, at least two of the reports including plots, extracting a plurality of variables from the plots, building a knowledge graph from the input, wherein each node of the knowledge graph is associated with an individual one of the plots and an edge is added between two of the nodes sharing at least one of the variables in common, adding an edge weight to each of the edges of the knowledge graph, and organizing the nodes of the knowledge graph for navigation, wherein the knowledge graph is displayed in a user interface.

Abstract: Embodiments describing an approach to aligning multiple time series, calculating an indicator function, estimating a coefficient vector based on the indicator function, and updating the coefficient vector. Additionally, embodiments comprise determining if a change in the coefficient vector is less than a predetermined value, and responsive to determining the change in the coefficient vector is less than the predetermined value outputting a target time series for controlling aluminum smelting.

Abstract: A first dependency graph is constructed based on a first data set by solving an objective function constrained with a maximum number of non-zeros and formulated with a regularization term comprising a quadratic penalty to control sparsity. The quadratic penalty in constructing the second dependency graph is determined as a function of the first data set. A second dependency graph is constructed based on a second data set by solving the objective function constrained with the maximum number of non-zeros and formulated with the regularization term comprising a quadratic penalty. The quadratic penalty in constructing the second dependency graph is determined as a function of the first data set and the second data set. An anomaly score is determined for each of a plurality of sensors based on comparing the first dependency graph and the second dependency graph, nodes of which represent sensors.

Abstract: Context-awareness in preventative maintenance is provided by receiving sensor data from a plurality of monitored systems; extracting a first plurality of features from a set of work orders for the monitored systems, wherein individual work orders include a root cause analysis for a context in which a nonconformance in an indicated monitored system occurred; predicting, via a machine learning model, a nonconformance likelihood for each monitored system based on the first plurality of features; selecting a subset of alerts based on predicted nonconformance likelihoods for the monitored systems; in response to receiving a user selection from the first set of alerts and a reason for the user selection, recording the reason as a modifier for the machine learning model; and updating the machine learning model to predict the subsequent nonconformance likelihoods using a second plurality of features that excludes the additional feature identified from the first plurality of features.

Abstract: A computer-implemented method for controlling a production system includes mapping, by a controller, the production system as a directed acyclic graph. The production system can include multiple plants that are represented as nodes and relations between the plants represented by edges of the directed acyclic graph. The method further includes generating, by the controller, a regression model for each of the plants in the production system. The method further includes predicting, by the controller, an output of each plant based on sensor data associated from each plant. The method further includes adjusting, by the controller, one or more control variables for each plant based on a target output by using machine learning. The method further includes adjusting, by the controller, the one or more control variables for each plant to generate the target output.

Abstract: Based on at least one manufacturing process characteristics associated with a manufacturing process, a prediction time at which to execute a selected machine learning model selected from multiple trained machine learning models is determined, and at the prediction time, the selected machine learning model is executed. Executing the selected machine learning model predicts a control set point for future values of state variables of the manufacturing process, for controlling the manufacturing process. Based on at least one of the manufacturing process characteristics, a learning time at which to train a machine learning model is determined, and at the learning time, the machine learning model is trained based on historical process data associated with the manufacturing process.

Abstract: Controlling product production in multi-stage manufacturing process automatically generates by machine learning causal relationships between the processing conditions and the product quality based on product genealogy data and product quality data. Real time sensor data from sensors coupled to processing units in a manufacturing facility implementing the multi-stage manufacturing process are received, and control rules are instantiated based on the real time sensor data. An instantiated control rule firing causes an actuator to automatically set a processing variable to a set point specified in the control rule.

Abstract: A system and a method of managing a manufacturing process includes receiving production data relating to the manufacturing process and determining an operational mode associated with the manufacturing process using historical, multivariate senor data. The method may further determine a recommended action to affect production based on the determined operational mode. The operational mode may be based on at least one of: a level of operation in a continuous flow process relating to a joint set of process variables, a representation of a joint dynamic of the set of process variables over a predefined length, and a joint configuration of an uptime/downtime of a plurality of units comprising a process flow.