Disclosed is an SNN circuit including a spike generator that receives an input spike signal and converts the input spike signal into a sub-spike signal and a main spike signal, a synaptic circuit that generates an operation signal based on a weight and outputs the operation signal in response to the main spike signal, a membrane capacitor that accumulates the operation signal, and a potential correction circuit that corrects an output terminal voltage of the synaptic circuit based on a voltage of the membrane capacitor.

Disclosed are a method for automatically diagnosing and controlling an apparatus in an intelligent building and relevant device. The method includes: performing, based on historical data of working parameters of multiple apparatuses, an abnormal diagnosis on received real-time data of the working parameters; determining an abnormal apparatus; selecting a neural network predictive control model corresponding to the abnormal apparatus; selecting one piece of non-abnormal data which has a same parameter type as that of the abnormal data and is close to the current abnormal data in time as a predictive control target, and determining a predictive control data that can cause an output matching the predictive control target; and controlling the abnormal apparatus according to the predictive control data. The automatic diagnosis and automatic control of an apparatus in an intelligent building are realized, meanwhile the safe and efficient operation of all apparatuses in an intelligent building is ensured.

A data processing system and a method are provided for acquiring data for training a machine learning (ML) model for use in self-monitoring the data processing system. The data processing system operates in a data acquisition mode to acquire training data for training the ML model. The training data is acquired from an anomaly detector of the data processing system while operating in the data acquisition mode. At least a portion of the training data is determined to be biased, and a portion of the training data is unbiased. The unbiased portion of the training data is transferred to a training environment external to the data processing system. The unbiased portion of the training data is acquired for training the ML model to function with the anomaly detector during a normal operating mode to determine when an anomaly is present in the data processing system.

Generating error event descriptions by receiving a set of error messages associated with an error event, generating a tokenization of at least one line of the set of error messages, providing the tokenization to an attention head according to a context of the tokenization, providing an output of the attention head as input to a generative model, generating a description of the error event according to the output, and providing the description to a user.

A method of estimating a toggle count of a circuit, includes, in part, simulating the circuit to generate training data and an associated training toggle count of the internal nodes of the circuit in response to a test bench, training a neural network system to generate an estimate of the training toggle count in accordance with the training data and the associated training toggle count, simulating the circuit to generate simulation data in response to a first set of input values applied to the circuit, and invoking the trained neural network system to estimate a number of toggles of the internal nodes of the circuit from the simulation data. The training data may include, in part, values of input signals applied to the circuit and values of registers disposed in the circuit for a multitude of time stamps. The neural network system may include, in part, at least three layers.

The invention relates to a fault diagnosis method for a rolling bearing under variable working conditions. Based on a convolutional neural network, a transfer learning algorithm is combined to handle the problem of the reduced universality of deep learning models. Data acquired under different working conditions is segmented to obtain samples. The samples are preprocessed by using FFT. Low-level features of the samples are extracted by using improved ResNet-50, and a multi-scale feature extractor analyzes the low-level features to obtain high-level features as inputs of a classifier. In a training process, high-level features of training samples and test samples are extracted, and a conditional distribution distance between them is calculated as a part of a target function for backpropagation to implement intra-class adaptation, thereby reducing the impact of domain shift, to enable a deep learning model to better carry out fault diagnosis tasks.

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 and systems for managing deployments are disclosed. A deployment may include one or more devices. The devices may include hardware and/or software components. The operation of the deployment may depend on the operation of these devices and components. To manage the operation of the deployment, a system may include a deployment manager. The deployment manager may obtain logs for components of the deployment reflecting the historical operation of these components and use the log to predict the future operation of the deployment. Based on the predictions, the deployment manager may take proactive action to reduce the likelihood of the deployment becoming impaired.

Example techniques may be implemented as a method, a system or more non-transitory machine-readable media storing instructions that are executable by one or more processing devices, Operations performed by the example techniques include obtaining data representing results of tests executed by one or more test instruments on an initial set of devices under test (DUTs) in a test system; and using the data to train a machine learning model. The machine learning model is for predicting which of the tests will produce failing results for a different set of DUTs. DUTs in the different set have one or more features in common with DUTs in the initial set.

A degraded user experience, such as a user having to wait for an unresponsive application, can be automatically detected and classified. A user experience degradation detection network detects a degraded user experience based on a state of the computing system and a user interaction state. The computing system state can be based on telemetry data provided by the operating system, processor units, and other computing system components and resources, and the user interaction state can be based on user interactions with one or more input devices (e.g., keyboard, touchpad, mouse, touchscreen). A root cause of the degradation event (e.g., hardware, memory, network, or general responsiveness issue) can be classified using a multi-label classifier. An output report can include a snapshot of the system telemetry and user interaction data before, during, and after the degradation event.