Abstract: Disclosed are a method and apparatus for energy-aware deep neural network compression. A network pruning method for deep neural network compression includes measuring importance scores of a network unit by using an energy-based criterion with respect to a deep learning model, and performing network pruning of the deep learning model based on the importance scores.

Abstract: Disclosed is an automatic lightweight method and apparatus for information flow-based neural network compression model that may preserve a performance. An automatic lightweight method for a neural network model may include receiving a first model, generating a second model by injecting trainable bottleneck parameters into the first model, training the bottleneck parameters of the second model using training data, determining an optimal threshold for the trained bottleneck parameters, and pruning the second model based on the trained bottleneck parameters and the determined optimal threshold.

Abstract: According to the embodiments of the present invention, the drive feel suitable to given conditions is provided to a driver by generating friction when a steering shaft is rotated to enhance the drive feel of the driver, limiting the maximum steering angle, restoring the steering wheel automatically, and controlling friction on the steering shaft in accordance with the steering angle, vehicle speed and road conditions.

Abstract: According to the embodiments of the present invention, the drive feel suitable to given conditions is provided to a driver by generating friction when a steering shaft is rotated to enhance the drive feel of the driver, limiting the maximum steering angle, restoring the steering wheel automatically, and controlling friction on the steering shaft in accordance with the steering angle, vehicle speed and road conditions.

Abstract: Disclosed are a method and apparatus for energy-aware deep neural network compression. A network pruning method for deep neural network compression includes measuring importance scores of a network unit by using an energy-based criterion with respect to a deep learning model, and performing network pruning of the deep learning model based on the importance scores.

Abstract: Pruning and/or quantizing a machine learning predictor or, in other words, a machine learning model such as a neural network is rendered more efficient if the pruning and/or quantizing is performed using relevance scores which are determined for portions of the machine learning predictor on the basis of an activation of the portions of the machine learning predictor manifesting itself in one or more inferences performed by the machine learning (ML) predictor.

Abstract: Disclosed herein is a stepping motor. The stepping motor include a bracket including a fixing hole; a shaft supporter rotatably supporting one end of a shaft and fitted into the fixing hole; and a pressure supporter pressing and supporting the fixing hole and the shaft supporter while forming a plurality of pressure support points between the fixing hole and the shaft supporter. As such, the plurality of pressure support points is formed between the shaft supporter and the fixing hole, thereby enabling the shaft supporter to be stably press-fitted into and fixed to the fixing hole of the bracket.