Samsung Electronics Co., Ltd.

Yunjae Lim

Sungho Kang

Jongyoub Ryu

Hyunsuk Min

Jaeeun Kang

Hyungdal Kwon

Sangsun Choi

Jieun Kim

Changseok Lee

Cheon An Lee

Changhan Kim

Junho Koh

Cheon Lee

Yonghyun Lim

Jaehong Kim

Hun Il Lim

Changhyun Lee

Jaewook Kim

Kyungjae Kim

Kwanwoo Song

Dongik Lee

Hyejung Cho

Chungyong Eom

Apoorv Kansal

Eunhui Bae

Hogun Lim

Junho Ko

Yoseong Song

Kyoungjin Moon

Manseok Kang

Hoejin Kwen

Yunho Park

Subyeong Oh

Byungcheol Yu

The present disclosure relates to an artificial intelligence (AI) system that utilizes a machine learning algorithm, and applications therefore. Disclosed is an electronic device. The electronic device comprises: a storage unit which stores therein an artificial intelligence model trained to determine parameters for a plurality of filters used for image processing on the basis of a deep neural network (DNN); and a processor for determining, through the artificial intelligence mode, parameters for each of the plurality of filters used for image processing for an input image, and performing, through the plurality of filters, filtering of the input image on the basis of the determined parameters so as to perform image processing for the input image.

Electronic device, image processing method of electronic device, and computer-readable medium

An encoding apparatus connected to a learning circuit processing learning of a deep neural network and configured to perform encoding for reconfiguring connection or disconnection of a plurality of edges in a layer of the deep neural network using an edge sequence generated based on a random number sequence and dropout information indicating a ratio between connected edges and disconnected edges of a plurality of edges included in a layer of the deep neural network.

Method of performing learning of deep neural network and apparatus thereof

The disclosure relates to an artificial intelligence (AI) system that simulates functions such as cognition and judgment of the human brain by utilizing machine learning algorithms such as deep learning and its applications. In particular, the disclosure provides a method of controlling data input and output of a fully connected network according to an artificial intelligence system and its applications, the method including receiving, from a learning circuit, an edge sequence representing a connection relationship between nodes included in a current layer of the fully connected network, generating a compressed edge sequence that compresses consecutive invalid bits among bit strings constituting the edge sequence into one bit and a validity determination sequence determining valid and invalid bits among the bit strings constituting the compressed edge sequence, writing the compressed edge sequence and the validity determination sequence to the memory, and sequentially reading the compressed edge sequences from the memory based on the validity determination sequence such that the valid bits are sequentially output to the learning circuit.

Method and device for controlling data input and output of fully connected network

An electronic device and a control method therefor are disclosed. A method for controlling an electronic device according to the present invention comprises the steps of: receiving a current frame; determining a region, within the current frame, where there is a movement, on the basis of a prior frame and the current frame; inputting the current frame into an artificial intelligence learning model on the basis of the region where there is the movement, to obtain information relating to at least one object included in the current frame; and determining the object included in the region where there is the movement, by using the obtained information relating to the at least one object. Therefore, electronic device can rapidly determine an object included in a frame configuring a captured image.

Electronic device and control method therefor

A device management method and apparatus is provided for managing electronic devices through wireless communication. A device management method of a first device having a list of wireless communication-enabled devices according to the present disclosure includes transmitting a first message requesting second device information, when it is necessary to check connection status of a second device performing wireless communication with the devices contained in the list, comparing the second device previously stored information and the second device information contained in the second message, when a second message including the second device information is received in response to the first message, and transmitting a recovery command message with the first device information, when the second device information included in the second message differs from the previously stored second device information.

Method and apparatus for managing electronic device through wireless communication

The present disclosure relates to a sensor network, Machine Type Communication (MTC), Machine-to-Machine (M2M) communication, and technology for Internet of Things (IoT). The present disclosure may be applied to intelligent services based on the above technologies, such as smart home, smart building, smart city, smart car, connected car, health care, digital education, smart retail, security and safety services. A method of managing an electronic device is provided, which includes determining a management target device, selecting at least one measurement device based on the determined management target device, transmitting an operation command to the management target device, receiving measurement information from the at least one measurement device, and determining a state of the management target device based on the received measurement information.

Method and apparatus for managing device using at least one sensor

A method according to an embodiment of the present invention relates to a method for automatically mapping a smart plug and an electronic device connected thereto in a home gateway. The method may comprise the steps of: deleting pre-stored mapping information when a signal received from the smart plug satisfies a condition requiring remapping to the electronic device; configuring a mapping candidate group on the basis of data included in the signal received from the smart plug and information stored for the electronic device when a status change notification signal is received from a predetermined electronic device within a preconfigured time; and when it can be determined that one particular electronic device from among the configured candidate group has been mapped to the smart plug, automatically mapping the corresponding electronic device and the smart plug in a state that the corresponding electronic device is connected to the smart plug.

Method for automatically mapping smart plug and electronic device connected thereto in home gateway and device therefor

The present disclosure relates generally to a sensor network, Machine Type Communication (MTC), Machine-to-Machine (M2M) communication, and technology for Internet of Things (IoT). The present disclosure may be applied to intelligent services based on the above technologies, such as smart home, smart building, smart city, smart car, connected car, health care, digital education, smart retail, security and safety services. A communication apparatus performs a method for determining a user's presence in a specific space. In the method, the apparatus receives a first signal from a first sensor and identifies a user access direction, based on the received first signal. Then, the apparatus selects a second sensor, based on the identified user access direction, receives a second signal from the selected second sensor, and determines whether a user enters in the specific space, based on the received second signal.

Apparatus and method for determining user's presence

Growing community of inventors

Seoul, South Korea

Yunjae Lim