Abstract: Methods, systems and computer readable media for isolating network faults are provided. A data driven automation services module is provided including a data connector, a data driven policy designer and a data driven self-service engine. The data connector collects data from the plurality of network data sources and integrates the data into shared communities for insight development. The data driven policy designer creates and stores templates and develops policies to implement service tasks to identify and isolate network problems. The data driven self-service engine integrates the network and its orchestration capabilities with big data technology to develop a plurality of microservices to perform service tasks.

Abstract: A failure analysis system identifies a root cause of a failure (or other health issue) in a virtualized computing environment and provides a recommendation for remediation. The failure analysis system uses a model-based reasoning (MBR) approach that involves building a model describing the relationships/dependencies of elements in the various layers of the virtualized computing environment, and the model is used by an inference engine to generate facts and rules for reasoning to identify an element in the virtualized computing environment that is causing the failure. Then, then the failure analysis system uses a decision tree analysis (DTA) approach to perform a deep diagnosis of the element, by traversing a decision tree that was generated by combining the rules for reasoning provided by the MBR approach, in conjunction with examining data collected by health monitors. The result of the DTA approach is then used to generate the recommendation for remediation.

Abstract: Out-of-bounds recovery circuits configured to detect an out-of-bounds violation in an electronic device, and cause the electronic device to transition to a predetermined safe state when an out-of-bounds violation is detected. The out-of-bounds recovery circuits include detection logic configured to detect that an out-of-bounds violation has occurred when a processing element of the electronic device has fetched an instruction from an unallowable memory address range for the current operating state of the electronic device; and transition logic configured to cause the electronic device to transition to a predetermined safe state when an out-of-bounds violation has been detected by the detection logic.

Abstract: A system includes a plurality of watchdog components. Each watchdog component is configured to receive a kick signal from its monitored function to determine whether the monitored function is active. Each watchdog component is further configured to receive a respective token from all watchdog components that the each watchdog component is connected to. The respective token determines whether its respective watchdog component has timed out. Each watchdog component is further configured to generate a token responsive to the kick signal and further responsive to the respective token from all watchdog component that the each watchdog component is connected to. Each watchdog component is further configured to transmit the generated token to the all watchdog components that the each watchdog component is connected to.

Abstract: Methods, systems, and devices for reporting control information errors are described. A state of a memory array may be monitored during operation. After detecting an error (e.g., in received control information), the memory device may enter a first state (e.g., a locked state) and may indicate to a host device that an error was detected, the state of the memory array before the error was detected, and/or at least a portion of a control signal carrying the received control information. The host device may diagnose a cause of the error based on receiving the indication of the error and/or the copy of the control signal. After identifying and/or resolving the cause of the error, the host device may transmit one or more commands (e.g., unlocking the memory device and returning the memory array to the original state) based on receiving the original state from the memory device.

Abstract: A method of monitoring a closed system, an apparatus thereof and a monitoring device are provided. The method of monitoring the closed system includes: performing a page capturing on a web page of the closed system; searching from a captured page, according to configuration information of data to be monitored of the closed system, a text content corresponding to the data to be monitored; and converting the text content corresponding to the data to be monitored into monitored data which a system monitoring platform is capable of recognizing, and storing the monitored data.

Abstract: An electronic evaluation device and method thereof for optimizing an operation of computer-controlled metric appliances in a network. The method includes determining whether a fault associated with computer-controlled metric appliance is valid based on a feedback received in real time from a validation entity and updating pre-defined programmable instructions assigned to the computer-controlled metric appliance in response to determining that the fault is invalid. The predefined programmable instructions are used to determine whether the computer-executable metric is achieved or not. The method includes applying a machine learning model on the plurality of parameters and the computer-executable goal to determine a computer-executable task list to be assigned to the computer-controlled metric appliance in order to achieve the computer-executable goal.

Abstract: Example implementations described herein involve a new data-driven analytical redundancy relationship (ARR) generation for fault detection and isolation. The proposed solution uses historical data during normal operation to extract the data-driven ARRs among sensor measurements, and then uses them for fault detection and isolation. The proposed solution thereby does not need to rely on the system model, can detect and isolate more faults than traditional data-driven methods, can work when the system is not fully observable, and does not rely on a vast amount of historical fault data, which can save on memory storage or database storage. The proposed solution can thereby be practical in many real cases where there are data limitations.

Abstract: A data processing pipeline may be generated to include an orchestrator node, a preparator node, and an executor node. The preparator node may generate a training dataset. The executor node may execute machine learning trials by applying, to the training dataset, a machine learning model and/or a different set of trial parameters. The orchestrator node may identify, based on a result of the machine learning trials, a machine learning model for performing a task. Data associated with the execution of the data processing pipeline may be collected for storage in a tracking database. A report including de-normalized and enriched data from the tracking database may be generated. The hyper-parameter space of the machine learning model may be analyzed based on the report. A root cause of at least one fault associated with the execution of the data processing pipeline may be identified based on the analysis.

Abstract: Computer systems and associated methods are disclosed to implement a model development environment (MDE) that allows a team of users to perform iterative model experiments to develop machine learning (ML) media models. In embodiments, the MDE implements a media data management interface that allows users to annotate and manage training data for models. In embodiments, the MDE implements a model experimentation interface that allows users to configure and run model experiments, which include a training run and a test run of a model. In embodiments, the MDE implements a model diagnosis interface that displays the model's performance metrics and allows users to visually inspect media samples that were used during the model experiment to determine corrective actions to improve model performance for later iterations of experiments. In embodiments, the MDE allows different types of users to collaborate on a series of model experiments to build an optimal media model.

Abstract: Remote access for debugging or profiling a remotely executing neural network graph can be performed by a client using an in-band application programming interface (API). The client can provide indicator flags for debugging or profiling in an inference request sent to a remote server computer executing the neural network graph using the API. The remote server computer can collect metadata for debugging or profiling during the inference operation using the neural network graph and send it back to the client using the same API. Additionally, the metadata can be collected at various granularity levels also specified in the inference request.

Abstract: Disclosed here is a system to automatically predict and reduce hardware related outages. The system can obtain a performance indicator associated with a wireless telecommunication network including a system performance indicator or an application log, along with a machine learning model trained to predict and resolve a hardware error based on the performance indicator. The machine learning model can detect an anomaly associated with the performance indicator by detecting an infrequent occurrence in the performance indicator. The machine learning model can determine whether the anomaly is similar to a prior anomaly indicating a prior hardware error. Upon determining that the anomaly is similar to the prior hardware error, the machine learning model can predict an occurrence of the hardware error.

Abstract: A parallel processing system includes at least three processors operating in parallel, state monitoring circuitry, and state reload circuitry. The state monitoring circuitry couples to the at least three parallel processors and is configured to monitor runtime states of the at least three parallel processors and identify a first processor of the at least three parallel processors having at least one runtime state error. The state reload circuitry couples to the at least three parallel processors and is configured to select a second processor of the at least three parallel processors for state reload, access a runtime state of the second processor, and load the runtime state of the second processor into the first processor. Monitoring and reload may be performed only on sub-systems of the at least three parallel processors. During reload, clocks and supply voltages of the processors may be altered. The state reload may relate to sub-systems.

Abstract: In one embodiment, a service identifies a set of attributes associated with a first machine learning model trained to make an inference about a computer network. The service obtains labels for each of the set of attributes, each label indicating whether its corresponding attribute is a probable cause of the inference. The service maps input features of the first machine learning model to those attributes in the set of attributes that were labeled as probable causes of the inference. The service generates a second machine learning model in part by using the mapped attributes to form a set of input features for the second machine learning model, whereby the input features of the first machine learning model and the input features of the second machine learning model differ.

Abstract: Disclosed are embodiments for improving remote diagnostics of a computer system. Some embodiments obtain operational parameter values and log data from a plurality of network devices, and provide the operational parameter values and log data to a machine learning model. The model is trained to identify a root cause of a degradation of the computer system based on the operational parameter values and log data, and to provide recommendations of log data level settings for the network devices. If the model identifies a root cause of the degradation with sufficient confidence, a remedial action is identified and applied to the computer system. If the confidence level is insufficient, log data level settings of the network devices are modified based on the recommendations of the model. This process is performed iteratively, for example, such that the model receives log data based on its recommended log data levels, until a root cause is identified with sufficient confidence.

Abstract: A computer-implemented method, a computer program product, and a computer system for diagnosing anomalies detected by a black-box machine learning model. A computer determines a local variance of a test sample in a test dataset, where the local variance represents uncertainty of a prediction by the black-box machine learning model. The computer initializes optimal compensations for the test sample, where the optimal compensations are optimal perturbations to test sample values of respective components of a multivariate input variable. The computer determines local gradients for the test sample. Based on the local variance and the local gradients, the computer updates the optimal compensations until convergences of the optimal compensations are reached. Using the optimal compensations, the computer diagnoses the anomalies detected by the black-box machine learning model.

Abstract: Exemplary methods, apparatuses, and systems include detecting a trigger to update a data integrity scan frequency. In response to detecting the trigger, an age indicator for a subdivision of memory or a utilization value for the subdivision of memory are obtained. A new data integrity scan frequency is determined using the age indicator or the utilization value. A scan of the subdivision of memory is initiated during a current media scan loop using the new data integrity scan frequency.

Abstract: The embodiments set forth a technique for enabling a computing device to cure a configuration issue associated with an auxiliary computing device. According to some embodiments, the technique can include the steps of (1) receiving, from the auxiliary computing device, a request to repair the configuration issue, where the request includes device information associated with the auxiliary computing device, and (2) in response to determining, based on the device information, that the auxiliary computing device is known to the computing device: (i) establishing a secure communication link with the auxiliary computing device, (ii) identifying at least one problem associated with the configuration issue, (iii) generating repair information based on the at least one problem, and (iv) transmitting the repair information to the auxiliary computing device over the secure communication link to cause the auxiliary computing device to cure the at least one problem.

Abstract: Systems and methods are provided for automatedly troubleshooting a computing application (e.g., a cloud-based computing application). An application domain of the computing application is modeled as a two-dimensional array of cells, a first dimension of the array representing components or microservices of the application domain, and a second dimension of the array representing states of the components or microservices, the array including paths between pairs of cells in the array. A troubleshooting goal is defined as a target state of the application domain, the target state corresponding to a target cell in the array. An initial state of the application domain is also provided, the initial state corresponding to an initial cell in the array. A reinforcement-learning-trained machine-learning algorithm can determine a solution path in the array between the initial cell and the target cell. Divergence between a failure case and a solution path indicates a probable failure cause.

Abstract: Detecting and remediating memory leaks associated with an application environment can include monitoring allocations of memory from a managed memory space to respective operations to produce memory allocation data and monitoring deallocations of memory to at least some of the respective operations to produce memory deallocation data. A trend in memory leakage can be determined based on samples of the memory allocation or deallocation data. A projection of future memory usage by operations associated with the trend can be determined using binned sets of the memory allocation data and the memory deallocation data. A predicted time at which memory usage by the operations associated with the trend is expected to exceed a threshold can be determined using the projection of future memory usage. A remediation action can be performed before the predicted time to prevent a memory constraint from occurring with respect to the application environment.