Abstract: Disclosed are an electronic device including a memory and a processor, and a method for controlling same. The memory stores a pre-trained neural network model and training data. The processor obtains a first loss function based on a label corresponding to the training data and output data obtained by inputting the training data into the neural network model; obtains a size of a change amount of a weight of each of a plurality of layers included in the neural network model based on the first loss function, and trains the neural network model by updating a weight of at least one layer for which the magnitude of the change amount of the weight exceeds a first threshold value, while at least one other layer, among the plurality of layers, for which a size of the weight change amount does not exceed the first threshold value is not updated.

Abstract: A decompression apparatus is provided. The decompression apparatus includes a memory configured to store compressed data decompressed and used in neural network processing of an artificial intelligence model, a decoder configured to include a plurality of logic circuits related to a compression method of the compressed data, decompress the compressed data through the plurality of logic circuits based on an input of the compressed data, and output the decompressed data, and a processor configured to obtain data of a neural network processible form from the data output from the decoder.

Abstract: An electronic apparatus is provided.

Abstract: An electronic apparatus is provided. The electronic apparatus includes a storage storing a matrix included in an artificial intelligence model, and a processor. The processor divides data included in at least a portion of the matrix by one of rows and columns of the matrix to form groups, clusters the groups into clusters based on data included in each of the groups, and quantizes data divided by the other one of rows and columns of the matrix among data included in each of the clusters.

Abstract: A method of controlling a notification output from an electronic device according to the present invention may comprise the steps of: outputting notification information; display a snoozing time setting object; using the displayed snoozing time setting object and setting a snoozing time; and executing a snoozing mode for the notification information, and re-outputting the notification information after the selected snoozing time elapses. However, the present invention is not limited to the above embodiment and may include other embodiments.

Abstract: Disclosed is an electronic device.

Abstract: A decompression apparatus is provided. The decompression apparatus includes a memory configured to store compressed data decompressed and used in neural network processing of an artificial intelligence model, a decoder configured to include a plurality of logic circuits related to a compression method of the compressed data, decompress the compressed data through the plurality of logic circuits based on an input of the compressed data, and output the decompressed data, and a processor configured to obtain data of a neural network processible form from the data output from the decoder.

Abstract: An electronic device is provided. The electronic device includes a memory storing parameter sets, each of which includes one weight and bias sets respectively corresponding to n (where, n>1) occlusion levels among a plurality of occlusion levels within a certain range and at least one processor configured to obtain output data by inputting input data to a neural network.

Abstract: A decompression apparatus is provided. The decompression apparatus includes a memory configured to store compressed data decompressed and used in neural network processing of an artificial intelligence model, a decoder configured to include a plurality of logic circuits related to a compression method of the compressed data, decompress the compressed data through the plurality of logic circuits based on an input of the compressed data, and output the decompressed data, and a processor configured to obtain data of a neural network processible form from the data output from the decoder.

Abstract: A decompression apparatus is provided. The decompression apparatus includes a memory configured to store compressed data decompressed and used in neural network processing of an artificial intelligence model, a decoder configured to include a plurality of logic circuits related to a compression method of the compressed data, decompress the compressed data through the plurality of logic circuits based on an input of the compressed data, and output the decompressed data, and a processor configured to obtain data of a neural network processible form from the data output from the decoder.

Abstract: A super-resolution processing method of a moving image is provided. The super-resolution processing method of a moving image includes sequentially inputting a plurality of input frames included in the video to any one of a recurrent neural network (RNN) for super-resolution processing and a convolutional neural network (CNN) for super-resolution processing, sequentially inputting a frame sequentially output from the any one of the RNN and the CNN to an additional one of the RNN and the CNN, and upscaling a resolution of the output frame by carrying out deconvolution with respect to a frame sequentially output from the additional one of the RNN and the CNN.

Abstract: An electronic apparatus is provided.

Abstract: A user terminal device includes a touch screen including a main display area and an auxiliary display area including a curved portion extending from the main display area, and a processor configured to, in response to an input for moving an icon displayed on the main display area to the auxiliary display area, control the touch screen to display the icon on the auxiliary display area.

Abstract: An electronic apparatus is provided. The electronic apparatus includes a storage storing a matrix included in an artificial intelligence model, and a processor. The processor divides data included in at least a portion of the matrix by one of rows and columns of the matrix to form groups, clusters the groups into clusters based on data included in each of the groups, and quantizes data divided by the other one of rows and columns of the matrix among data included in each of the clusters.

Abstract: The present disclosure relates to system resource management in a variety of situations. The present disclosure provides a method and an apparatus for reducing memory requirements and improving processing speed when an electronic device performs padding for a particular arithmetic operation on data. To achieve the above objective, a method for operating an electronic device according to the present disclosure comprises the steps of: reading a first portion of data from a first memory; determining a first padding address based on the address of a byte belonging to a boundary region of the data among a plurality of bytes included in the first portion; writing values of the plurality of bytes and a value corresponding to the first padding address to a second memory; and reading a second portion of the data from the first memory.

Abstract: The present disclosure relates generally to technologies for sensor networks, machine-to-machine (M2M), machine-type communication (MTC), and Internet of things (IoT). The present disclosure may be used in intelligent services (smart home, smart building, smart city, smart car, or connected car, health-care, digital education, retail business, security and safety-related services, etc.), or the like, without limitation.

Abstract: An electronic device is provided. The electronic device includes a memory storing parameter sets, each of which includes one weight and bias sets respectively corresponding to n (where, n>1) occlusion levels among a plurality of occlusion levels within a certain range and at least one processor configured to obtain output data by inputting input data to a neural network.

Abstract: The present disclosure relates to system resource management in a variety of situations. The present disclosure provides a method and an apparatus for reducing memory requirements and improving processing speed when an electronic device performs padding for a particular arithmetic operation on data. To achieve the above objective, a method for operating an electronic device according to the present disclosure comprises the steps of: reading a first portion of data from a first memory; determining a first padding address based on the address of a byte belonging to a boundary region of the data among a plurality of bytes included in the first portion; writing values of the plurality of bytes and a value corresponding to the first padding address to a second memory; and reading a second portion of the data from the first memory.

Abstract: A super-resolution processing method of a moving image is provided. The super-resolution processing method of a moving image includes sequentially inputting a plurality of input frames included in the video to any one of a recurrent neural network (RNN) for super-resolution processing and a convolutional neural network (CNN) for super-resolution processing, sequentially inputting a frame sequentially output from the any one of the RNN and the CNN to an additional one of the RNN and the CNN, and upscaling a resolution of the output frame by carrying out deconvolution with respect to a frame sequentially output from the additional one of the RNN and the CNN.

Abstract: A method of controlling a notification output from an electronic device according to the present invention may comprise the steps of: outputting notification information; display a snoozing time setting object; using the displayed snoozing time setting object and setting a snoozing time; and executing a snoozing mode for the notification information, and re-outputting the notification information after the selected snoozing time elapses. However, the present invention is not limited to the above embodiment and may include other embodiments.