Samsung Electronics Co., Ltd.

Chiyoun Park

Hyunjoo Jung

Inkwon Choi

Youngchul Sohn

Ilgu Kang

Sunghyun Choi

Juyong Song

Changhyun Lee

Jaewon Lee

Kyungmin Lee

Dongjae Lim

Joohyung Lee

Namhoon Kim

Jongyoub Ryu

Changwoo Han

Jaedeok Kim

Jungwook Kim

Youngho Han

Jaeyoung Roh

Keunseok Cho

Kangwook Lee

Byeongcheol Kang

Jungmin Kwon

Hyunseo Park

Jeongseop Kim

Donguk Ju

Gyujeong Hwang

A controlling method of an electronic device are provided. The controlling method includes obtaining, a first feature value corresponding to the input data, mapping information included in the first feature value to a symbolic value corresponding to each of a logically certain information and uncertain information, tweaking a gradient corresponding to the uncertain information, obtaining a second feature value in which the first feature value and the symbolic value are merged, obtaining temporary answer information including the certain information and the uncertain information, obtaining score information related to a level the temporary answer information matches a pre-defined logic rule, training the neural network model based on the tweaked gradient when the score information is less than a pre-set threshold value, and obtaining an output data on the input data based on the obtained second feature value when the score information is greater than or equal to the pre-set threshold value.

Electronic device and controlling method of electronic device for applying a logical constraint to a neural network model

A method of controlling an electronic apparatus for generating an artificial intelligence model is disclosed. The method includes based on a user command for using a plurality of artificial intelligence models being input, generating the plurality of artificial intelligence models, and inputting input data to the generated artificial intelligence model to obtain output data with respect to the input data, wherein the generating includes, based on a reference value for obtaining a layer parameter with respect to layers at corresponding locations among a plurality of layers included in each of the plurality of artificial intelligence model, generating layers at corresponding locations among layers included in each of the plurality of artificial intelligence models.

Electronic apparatus and method of controlling thereof

An electronic device and a control method therefor are provided. The electronic device may comprise: a memory for storing at least one instruction; and a processor connected to the memory so as to control the electronic device, wherein the processor: by executing the at least one instruction, appends a second layer including a learnable function to a first layer in an artificial neural network including a plurality of layers; updates a parameter value included in the second layer by learning of the artificial neural network; acquires a function value by inputting the updated parameter value to the learnable function; and eliminates at least one channel among a plurality of channels included in the first layer on the basis of the acquired function value so as to achieve update to a third layer.

Electronic device and control method therefor

An electronic apparatus is provided. The apparatus includes a communicator, a memory configured to store a neural network model, an activation function generating module that generates activation function information used in the neural network model, first activation function information, second activation function information, and third activation function information generated based on the first activation function information and the second activation function information, and a processor configured to receive fourth activation function information from an external device through the communicator, based on type information on the fourth activation function information corresponding to the second activation function information, input the first activation function information and the fourth activation function information to the activation function generating module to generate fifth activation function information, and control the neural network model to change the activation function information used in the neural network model from the third activation function information to the fifth activation function information.

Provided are an electronic device for navigating an application screen, and an operating method thereof. The method may include receiving a user input; determining, based on the user input, a user intent for controlling the electronic device; determining a command for performing a control operation corresponding to the user intent as a goal; identifying elements of a user interface on the screen of the application; determining, based on the user intent and the elements of the user interface, at least one sub-goal for executing the command; and executing the command by performing at least one task corresponding to the at least one sub-goal, wherein the at least one sub-goal is changeable based on a validation of an operation of navigating the application for executing the command, and the at least one task includes units of action for navigating the application.

Method and electronic device for navigating application screen

An electronic device and a method for controlling thereof is provided. The electronic device includes a memory including a neural network model, a display, a communicator including circuitry, and a processor configured to identify, based on a user command to transmit a first image to an external device being input, whether private information of a user is included in the first image by inputting the first image in the neural network model, based on identifying that private information of the user is included in the first image, display a first user interface (UI) asking whether to process at least one private information based on the private information included in the first image, and based on a user command input through the first UI, process the first image and control the communicator to transmit the processed to the external device.

Electronic device and method for controlling thereof

Disclosed is an electronic apparatus. The electronic apparatus may include a memory configured to store one or more training data generation models and an artificial intelligence model, and a processor configured to generate personal training data that reflects a characteristic of a user using the one or more training data generation models, train the artificial intelligence model using the personal learning data as training data, and store the trained artificial intelligence model in the memory.

Method and apparatus for artificial intelligence model personalization

An electronic device for reconstructing an artificial intelligence model, and a control method thereof are provided. The control method includes inputting at least one input data to a first artificial intelligence (AI) model, to acquire at least one output data, acquiring first usage information, based on the acquired at least one output data, acquiring first reconstruction information for reconstructing the first AI model, based on the acquired first usage information, and reconstructing the first AI model, based on the acquired first reconstruction information, to acquire a second AI model.

Electronic device for reconstructing an artificial intelligence model and a control method thereof

Provided is an apparatus configured to determine a common neural network based on a comparison between a first neural network included in a first application program and a second neural network included in a second application program, utilize the common neural network when the first application program or the second application program is executed.

Apparatus and method for managing application program

An electronic apparatus for compressing a neural network model may acquire training data pairs based on an original, trained neural network model and train a compressed neural network model compressed from the original, trained neural network model using the acquired training data pairs.

Neural network model apparatus and compressing method of neural network model

A method of processing a speech signal for speaker recognition in an electronic apparatus includes: obtaining a speech signal of a first user; extracting a speech feature comprising a feature value from the speech signal; comparing the speech feature extracted from the speech signal of the first user with a predetermined reference value; selecting a first user feature that corresponds to the speech feature of the first user compared with the reference value; generating a recommended phrase used for speaker recognition based on the first user feature; and outputting the recommended phrase.

Growing community of inventors

Suwon-si, South Korea

Chiyoun Park