An electronic apparatus including a memory; and a processor including at least one core, among a plurality of cores, that is configured to execute an instruction corresponding to at least one safety function. The processor is further configured to, based on at least one instruction being executed in the at least one core while the electronic apparatus operates in a first state, identify whether the at least one instruction corresponds to the safety function based on an output of a trained neural network model; and based on a result of the identification, determine an operation state of the electronic apparatus as one of the first state or a second state.

A test system including an embodiment having a sensor array adapted to test one or more devices under test in learning modes as well as evaluation modes. An exemplary test system can collect a variety of test data as a part of a machine learning system associated with known-good samples. Data collected by the machine learning system can be used to calculate probabilities that devices under test in an evaluation mode meet a condition of interest based on multiple testing and sensor modalities. Learning phases or modes can be switched on before, during, or after evaluation mode sequencing to improve or adjust machine learning system capabilities to determine probabilities associated with different types of conditions of interest. Multiple permutations of probabilities can collectively be used to determine an overall probability of a condition of interest which has a variety of attributes.

A deep learning fault diagnosis method includes the following steps: a fault diagnosis data set X is processed based on sliding window processing, to obtain a picture-like sample data set {tilde over (X)}, and obtain an attention matrix A of the picture-like sample data set {tilde over (X)}; and a 2D-CNN model is constructed to process the picture-like sample data set {tilde over (X)} to obtain a corresponding feature map F, and in the meantime, the feature map F is processed based on channel-oriented average pooling and channel-oriented maximum pooling to obtain an output P.sub.1 of the average pooling and an output P.sub.2 of the maximum pooling, and a weight matrix W is obtained based on the attention matrix A, the output P.sub.1 of the average pooling, and the output P.sub.2 of the maximum pooling, so that an output of the model is a feature map {tilde over (F)} based on an attention mechanism, where {tilde over (F)}=WF.

Systems and methods for proactive support of computing assets are presented. In contrast to existing techniques of reactive support, the proactive support techniques disclosed herein automatically collect operating data from a plurality of computing devices, analyze the operating data to identify predictive indicators associated with error conditions, identify a subset of affected computing devices that match the predictive indicators, and execute corrective scripts to remediate or avoid such error conditions before problems are experienced on the affected computing devices. The operating data may be used to train a machine learning model in order to identify the predictive indicators associated with each error condition. In some embodiments, the corrective scripts may be automatically generated to adjust operating parameters or applications of the affected computing devices based upon the identified predictive indicators.

Methods for system failure prediction include clustering log files according to structural log patterns. Feature representations of the log files are determined based on the log clusters. A likelihood of a system failure is determined based on the feature representations using a neural network. An automatic system control action is performed if the likelihood of system failure exceeds a threshold.

A system and method include a printing system with printing modules through which print media is transferred. The printing modules include sensors and a fault detection component. A printing system includes a fault identification system (FIS) and a scheduler. The FIS includes, a machine learning component, a Dependency-matrix component and an optimal search component. The optimal search component repeatedly implements a Rate of Return (ROR) that links the probabilities of occurrences of faults to a priori probabilities of faults and a detection function of the ROR to elements of the D-matrix, determines a ROR value, provides a benefit, and sends one more test to a scheduler of the printing system, which then physically implements the one more test. The prior steps are repeated until a stopping condition is reached and a fault is diagnosed.

Methods, apparatus, and processor-readable storage media for determining configurations to be used in system testing processes using machine learning techniques are provided herein. An example computer-implemented method includes obtaining, from multiple data sources, configuration information associated with at least one system; filtering out a subset of the configuration information based at least in part on at least one user request related to testing of at least a portion of the at least one system; determining at least a portion of the subset of the configuration information to be used in the testing of the at least a portion of the at least one system by processing the subset of the configuration information using one or more machine learning techniques; and performing one or more automated actions based on the determined at least a portion of the subset of the configuration information to be used in the testing.

A system in package platform includes a processor chip having a runtime processor core, an accelerator core and a processor-memory interface exposed on a chip-to-chip bonding surface, a first memory chip such as 3D NAND flash memory storing a collection of executable models of inference engines, and a second memory chip storing weights of a selected executable model. The second memory chip can comprise a nonvolatile, random access memory, such as phase change memory. Direct vertical connections such as via-to-via connections, are provided between the processor chip and the second memory chip.

A machine learning module is trained by receiving inputs comprising attributes of a computing environment, where the attributes affect a likelihood of failure in the computing environment. In response to an event occurring in the computing environment, a risk score that indicates a predicted likelihood of failure in the computing environment is generated via forward propagation through a plurality of layers of the machine learning module. A margin of error is calculated based on comparing the generated risk score to an expected risk score, where the expected risk score indicates an expected likelihood of failure in the computing environment corresponding to the event. An adjustment is made of weights of links that interconnect nodes of the plurality of layers via back propagation to reduce the margin of error, to improve the predicted likelihood of failure in the computing environment.

A method for repairing a memory element in a memory device by an electronic device includes configuring a memory element as a graph with a vertex and an edge, a node associated with the memory element being encoded with information related to a fault, determining, from the graph, a repair policy using a probability distribution over one or more of a faulty line and a non-faulty line as predicted by a graph neural network (GNN) based on a final node feature value from message passing stages of the GNN, and determining a value of a state using a probability of the memory element being repaired from a particular state based on a global mean of all the final node feature values predicted by the GNN.