A method and an electronic device for selecting deep neural network hyperparameters are provided. In an embodiment of the method, a plurality of testing hyperparameter configurations are sampled from a plurality of hyperparameter ranges of a plurality of hyperparameters. A target neural network model is trained by using a training dataset and the plurality of testing hyperparameter configurations, and a plurality of accuracies corresponding to the plurality of testing hyperparameter configurations are obtained after training for preset epochs. A hyperparameter recommendation operation is performed to predict a plurality of final accuracies of the plurality of testing hyperparameter configurations. A recommended hyperparameter configuration corresponding to the final accuracy having a highest predicted value is selected as a hyperparameter setting for continuing training the target neural network model.

A method, apparatus, computer system, and computer program product for managing a device. The method detects, by a computer system, a physical handling of the device to form a physical handling pattern for the device. The method determines, by the computer system, a baseline physical handling pattern for the device, wherein the baseline physical handling pattern for the device meets a set of handling metrics for the device. The method initiates, by the computer system, a set of actions in response to the physical handling pattern for the device deviating from the baseline physical handling pattern for the device.

A data store system may include at least one storage device to store a plurality of data and at least one processor with access to the storage device. The at least one processor may receive a plurality of features associated with an environment. The at least one processor may further generate a state representation of the environment based on the plurality of features. The at least one processor may further generate a plurality of predicted future states of the environment based on the state representation. The at least one processor may further generate at least one action to be performed by the environment based on the plurality of predicted future states. The at least one processor may provide the at least one action to the environment to be performed. A method and computer-readable medium are also disclosed.

Disclosed are a multi-task training technique and resulting model for detecting distracted driving. In one embodiment, a method is disclosed comprising inputting a plurality of labeled examples into a multi-task network, the multi-task network comprising: a backbone network, the backbone network generating one or more feature vectors corresponding to each of the labeled examples, and a plurality of prediction heads coupled to the backbone network; minimizing a joint loss based on outputs of the plurality of prediction heads, the minimizing the joint loss causing a change in parameters of the backbone network; and storing a distraction classification model after minimizing the joint loss, the distraction classification model comprising the parameters of the backbone network and parameters of at least one of the prediction heads.

A method and system for performing semi or fully automatic data imbalance detection and correction in training a machine-learning (ML) model includes receiving a request to train the ML model, receiving access to a dataset for use in training the ML model, identifying a feature of the dataset for which data imbalance detection is to be performed, examining the dataset to determine a distribution of the feature across the dataset, determining if the distribution of the feature across the dataset indicates data imbalance, upon determining that the distribution of the feature across the dataset indicates data imbalance, identifying a desired distribution for the identified feature, selecting a subset of the dataset that corresponds with the selected feature and the desired distribution, and using the subset to train the ML model.

Method and system of training a machine learning neural network (MLNN). The method comprises receiving a set of input features at respective input layers of the MLNN. The MLNN implemented in a processor and comprises an output layer interconnected to input layers via intermediate layers. The input features are associated with input feature data of a patient medical condition. Then selecting, responsive to a data qualification threshold level, a subset of the input layers while deactivating a remainder of the set of input layers. The intermediate layers are configured with an initial matrix of weights. Then training the MLNN based at least in part upon adjusting the initial matrix of weights based on a supervised classification that provides, via the output layer, one of negative and positive patient diagnostic states.

Provided is a reservoir computing system including a reservoir having a random laser for emitting a non-linear optical signal with respect to an input signal. The reservoir computing system also includes a converter for converting the non-linear optical signal into an output signal by applying a conversion function. The conversion function is trained by using a training input signal and a target output signal.

A multi-agent simulation system performs a simulation of a target world in which a plurality of agents interacting with each other exist. The multi-agent simulation system includes: a plurality of agent simulators configured to perform simulations of the plurality of agents, respectively; and a center controller configured to communicate with the plurality of agent simulators. Operation modes of the center controller include: a first mode that does not perform message filtering; and a second mode that performs the message filtering. When the number of messages that the center controller receives per unit time is equal to or less than a threshold, the center controller selects the first mode. On the other hand, when the number of result messages that the center controller receives per unit time exceeds the threshold, the center controller selects the second mode.

Clustering can be performed using a self-expression matrix in which noise is suppressed. A self-expression matrix is calculated that minimizes an objective function that is for obtaining, from among matrices included in a predetermined matrix set, a self-expression matrix whose elements are linear weights when data points in a data set are expressed by linear combinations of points, the objective function being represented by a term for obtaining the residual between data points in the data set and data points expressed by linear combinations of points using the self-expression matrix, a first regularization term that is multiplied by a predetermined weight and is for reducing linear weights of the data points that have a large Euclidean norm in the self-expression matrix, and a second regularization term for the self-expression matrix. A similarity matrix defined by the calculated self-expression matrix is then calculated. Then a clustering result is obtained by clustering the data set based on the similarity matrix.

A method for anomaly detection and troubleshooting in a network includes parsing a network service descriptor (NSD) describing a network service (NS) to be deployed in the network. Monitoring data including time series of service-level metrics and resource-level metrics of network functions (NFs) of the NS are received from different domains of the network. Representations of the time series from the different domains are learned with a common dimensionality. An NS signature of the NS is computed as a cross-correlation matrix comprising cross-correlations between the service-level metrics and the resource-level metrics of the NFs. Embeddings of the NS signature are learned using a model and determining a reconstruction error of the model. It is determined whether the NS is anomalous based on the reconstruction error of the model. The NS is identified as a target for the troubleshooting in a case that the NS was determined to be anomalous.