Samsung Sds Co., Ltd.

Nota, Inc.

Geun Jae Lee

Jong Won Baek

Yoo Chan Kim

Disclosed is a method of compressing a neural network model that is performed by a computing device. The method includes receiving a trained model and compression method instructions for compressing the trained model, identifying a compressible block and a non-compressible block among a plurality of blocks included in the trained model based on the compression method instructions, transmitting a command to a user device that causes the user device to: display a structure of the trained model representing a connection relationship between the plurality of blocks on a first screen such that the compressible block and the non-compressible block are visually distinguished, and display, on a second screen, an input field operable to receive a parameter value entered by a user for compression of the compressible block, and compressing the trained model based on the parameter value entered by the user in the input field.

Method of compressing neural network model and electronic apparatus for performing the same

Provided is a method of extending participants of a multilateral video conference service. The method includes: receiving, by a multipoint conference unit (MCU) gateway connected with an MCU through at least one physical port and connected with a plurality of terminals in a wired or wireless manner, information on a signal level of sound sensed by microphones provided in plurality of terminal devices from plurality of terminal devices, respectively, selecting, by MCU gateway, one terminal device among plurality of terminal devices as a speaking terminal device based on the received signal level, requesting, by MCU gateway, speaking terminal device to transmit speaking contents input into speaking terminal device and transmitting, by the MCU gateway, speaking contents received from speaking terminal device in response to transmission request to the MCU through at least one physical port.

Growing community of inventors

Seoul, South Korea

Geun Jae Lee