Samsung Electronics Co., Ltd.

Vivid Engineering, Inc.

Pavel Biryulin

Vladislav Potanin

Elena Potanina

Valery Valerievich Anisimovskiy

George McLean

Andrei Yurievich Shcherbinin

A neural network model training apparatus for enhancing image detail is provided. The apparatus includes a memory and at least one processor configured to obtain a low quality input image patch and a high quality input image patch, obtain a low quality output image patch by inputting the low quality input image patch to a first neural network model, obtain a high quality output image patch by inputting the high quality input image patch to a second neural network model, and train the first neural network model based on a loss function set to reduce a difference between the low quality output image patch and the high quality input image patch, and a difference between the high quality output image patch and the high quality input image patch. The second neural network model is identical to the first neural network model.

Method and apparatus for training neural network model for enhancing image detail

Technologies are generally described for scaling a voltage regulator implemented as an integrated circuit (IC) that includes a power transistor configured to convert an input voltage to an output voltage, and a feedback loop configured to regulate the output voltage in response to a voltage change. At least one component of the voltage regulator may be selected for scaling, and a range of scaling factors may be identified for the component. An optimal coefficient may be determined for the scaling factors within the identified range through an empirical formulation and/or by running a circuit simulation based on parameters associated with voltage, load current, and load capacitance, for example. The optimal coefficient may be a coefficient that when applied to the component optimizes the performance of the IC and thus, the component may be scaled based on the optimal coefficient to achieve an optimized performance of the IC.

Scaling voltage regulators to achieve optimized performance

Growing community of inventors

Moscow, Russia

Pavel Biryulin