Abstract: A processor-implemented method with pruning including deactivating input channels and output channels of layers of a target model, each layer of the layers including a convolutional layer and a fully-connected layer, determining, based on a dependency relationship among the layers, a network segment set, each network segment in the network segment set including one or more of an input channel and an output channel having a dependency, an individual input channel, and an individual output channel in the target model, and activating, based on a respective importance of each network segment in the network segment set, channels of a determined number of network segments of the target model.

Abstract: A superconducting motor system includes a stator and one or more rotors inside the stator. The rotors may form a plurality of poles, and may rotate when a current is applied thereto. The one or more rotors include: a superconductor winding portion for each pole and in which superconductor coils are wound to form at least two layers; a power supply portion configured to supply a current to the superconductor winding portion; and a resistor portion connecting the superconductor winding portion at least partly in parallel to the power supply portion. the resistor portion enables different currents to be able to flow through the at least two layers of the superconductor winding portion.

Abstract: A processor-implemented method including, based on a first shape of a first tensor and a second shape of a second tensor used in an operation with the first tensor, determining a broadcasting type related to an extension of the first shape and the second shape, determining respective first shape offsets for each dimension of the first shape and respective second shape offsets for each dimension of the second shape based on the broadcasting type, determining respective first tensor offsets for each dimension of the first tensor and respective second tensor offsets for each dimension of the second tensor based on the broadcasting type, the respective first shape offsets for each dimension of the first shape, and the respective second shape offsets for each dimension of the second shape, determining a first offset of a first element included in the first tensor and a second offset of a second element included in the second tensor based on the respective first tensor offsets and the respective second tensor offse

Abstract: A method performed by one or more processors includes: iteratively training layer-specific quantization levels and layer-specific quantization intervals of respective layers of a neural network of original weights by, for each training iteration, adjusting the quantization levels and quantization intervals to reduce a loss that is determined based on the original weights and is determined based on the original weights as quantized according to the quantization levels and quantization intervals at a current iteration of the training.

Abstract: A method and device with federated learning of neural network models are disclosed. A method includes: receiving weights of respective clients, wherein each weight has a respectively corresponding precision that is initially an inherent precision; using a dequantizer to change the weights such that the precisions thereof are changed from the inherent precisions to a same reference precision; determining masks respectively corresponding to the weights based on the inherent precisions; based on the masks, determining an integrated weight by merging the weights having the reference precision; and quantizing the integrated weight to generate quantized weights having the inherent precisions, respectively, and transmitting the quantized weights to the clients.

Abstract: A method of searching for hyperparameters for neural network learning includes: obtaining a preset early stop point; determining whether a current trial, among trials for searching for different combinations of hyperparameters, corresponds to a dry run trial; in response to a determination that the current trial corresponds to a dry run trial: executing learning epochs belonging to the current trial; searching for a combination of hyperparameters assigned to the current trial according to a result of the executing of the learning epochs; and changing the early stop point by based on whether an early stop with respect to a found combination of the hyperparameters is a success in each of the learning epochs.

Abstract: A superconducting motor system includes a stator and one or more rotors inside the stator. The rotors may form a plurality of poles, and may rotate when a current is applied thereto. The one or more rotors include: a superconductor winding portion for each pole and in which superconductor coils are wound to form at least two layers; a power supply portion configured to supply a current to the superconductor winding portion; and a resistor portion connecting the superconductor winding portion at least partly in parallel to the power supply portion. the resistor portion enables different currents to be able to flow through the at least two layers of the superconductor winding portion.

Abstract: A method of a system including a processor including recording experiment information of a job in connection with job information generated based on an execution of a job of a computer cluster system, and controlling further execution of a job, by the computer cluster system, by transmitting a change in the experiment information to the computer cluster system based on the job information.

Abstract: A processor-implemented method of tracking a target object includes: extracting a feature from frames of an input image; selecting one a neural network model from among a plurality of neural network models that is provided in advance based on a feature value range, based on a feature value of a target object that is included in the feature of a previous frame among the frames; and generating a bounding box of the target object included in a current frame among the frames, based on the selected neural network model.

Abstract: A processor-implemented method of tracking a target object includes: extracting a feature from frames of an input image; selecting one a neural network model from among a plurality of neural network models that is provided in advance based on a feature value range, based on a feature value of a target object that is included in the feature of a previous frame among the frames; and generating a bounding box of the target object included in a current frame among the frames, based on the selected neural network model.

Abstract: A mobile device with a laser direct structuring (LDS) antenna module is provided in the present disclosure. The mobile device includes a glass back cover and an LDS antenna module on the glass back cover. The LDS antenna module includes an LDS coating layer formed on a main surface of the glass back cover, and at least one antenna unit formed at the LDS coating layer by LDS process. The present disclosure also provides a method for making an LDS antenna module.