Neural network learning method and device

    公开(公告)号:US11586923B2

    公开(公告)日:2023-02-21

    申请号:US16645158

    申请日:2018-09-06

    Abstract: The disclosure relates to an artificial intelligence (AI) system for mimicking functions, such as cognition and determination as of the human brain, by utilizing a machine learning algorithm such as deep learning, and an application thereof. Provided are a neural network learning method according to an AI system and applications thereof, the method including extracting, by using a masking filter having an effective value in a specific portion of the masking filter including weight information of at least one hidden layer included in a learning network model, characteristics of input data according to weight information of a filter corresponding to the specific portion, comparing output data with target data, the output data being obtained from the learning network model based on extracted characteristics of the input data, and updating a size of the specific portion having the effective value in the masking filter, based on a result of the comparing.

    System and method of providing object for service of service provider

    公开(公告)号:US11455675B2

    公开(公告)日:2022-09-27

    申请号:US16134562

    申请日:2018-09-18

    Abstract: A server and method of providing an object for accessing a service of a service provider are provided. The server includes a context model providing unit configured to provide to the service provider at least one context model that is associated with the service, which is used by a device or a user, and a situation in which the device or the user uses the service; a purchase request receiving unit configured to receive a purchase request submitted by the service provider for a context model which is selected from among the at least one context model; and an object generation unit configured to generate the object for accessing the service of the service provider. The generated object is matched with the context model associated with the purchase request received from the service provider.

    Neural network learning method and device for recognizing class

    公开(公告)号:US11449733B2

    公开(公告)日:2022-09-20

    申请号:US16645344

    申请日:2018-09-04

    Abstract: The present disclosure provides a neural network training device for recognizing a class of an object included in an image based on an artificial intelligence (AI) system and an application thereof, the neural network training method including: acquiring, by using a first learning network model trained based on source training images respectively included in at least one class, feature information of a query image included in a class different from the at least one class; obtaining a generated image from the feature information of the query image by using a second learning network model acquiring feature information of the obtained generated image by using the first learning network model; and updating weights of layers respectively included in the first and second learning network models, based on a difference between the feature information of the query image and the feature information of the generated image and on a difference between the query image and the generated image.

    Method for synthesizing image and an electronic device using the same

    公开(公告)号:US11145047B2

    公开(公告)日:2021-10-12

    申请号:US16026687

    申请日:2018-07-03

    Abstract: An apparatus and method for synthesizing an image and an electronic apparatus using the method are provided. The electronic apparatus includes a memory that stores pictures, a transceiver that communicates with an external server, a display that detects a user interaction, and a processor that reads pictures from the memory. The processor first selects pictures based on a weighted value, determines first attribute information and second attribute information from the first selected pictures, stores the first attribute information and the second attribute information in a database form, second selects at least one picture from among the first selected pictures based on the first attribute information, the second attribute information and user context information, controls the transceiver to receive a product image corresponding to the second selected picture from the external server, and creates a composite image by synthesizing the second selected picture and the product image.

    Electronic device, system including electronic device and relay apparatus, and control method for the same

    公开(公告)号:USRE48496E1

    公开(公告)日:2021-03-30

    申请号:US16270221

    申请日:2019-02-07

    Abstract: An electronic apparatus controls a peripheral device by using a relay apparatus. The electronic apparatus includes an interface connected to the peripheral device; a communication unit that performs communication with the relay apparatus; a receiver that receives a control signal for controlling the electronic apparatus; and a controller that, when the control signal is received, performs an operation based on the control signal, and controls the communication unit to transmit information about the performed operation and information about the peripheral device to the relay apparatus in order to control the peripheral device to perform an operation that corresponds to the performed operation.

Patent Agency Ranking