Samsung Electronics Co., Ltd.

Seoul National University

Yoojin Kim

Channoh Kim

Hyunsun Park

Jun-Woo Jang

Sehwan Lee

Donghyun Kang

Jintaek Kang

Soonhoi Ha

Hyunggon Lee

Yunhui Cho

Jongchul Choi

Saehee Lee

Junwoo Jang

Hyeongseok Yu

Hwanju Jeon

Sejin Kim

Junsang Park

Hyun Sun Park

Jinchoul Park

Soonwoo Kwon

Soonho Han

Wanju Shin

Younggoo Kang

Gijea Park

A memory mapping method includes storing a feature map including a plurality of sets of data used for a neural network operation in a memory, shifting a position of a portion of the data included in the feature map that is stored in the memory based on a parameter of the neural network operation, and outputting data requested by the neural network operation from the feature map in which the position of the portion is shifted based on a memory bandwidth.

Memory mapping method and apparatus

An electronic device according to various embodiments of the disclosure may include a housing including a first plate forming an outer face. The first plate may include a glass plate including a first surface outwardly facing the housing and a second surface inwardly facing the housing, a coating layer including an anti-reflection coating and/or an anti-finger coating above the first surface while forming the outer face, a first layer formed between the first surface of the first glass plate and the coating layer, having a first thickness, and including a first inorganic material, a second layer formed between the first layer and the coating layer, having a second thickness, and including a second inorganic material different from the first inorganic material, a third layer formed between the second layer and the coating layer, having a third thickness thicker than each of the first thickness and the second thickness, and including a third inorganic material, and an opaque layer formed on the second surface. Various other embodiments may also be possible.

Electronic device comprising high hardness color structure layer

A computing method and device with data sharing are provided. The method includes loading, by a loader, input data of an input feature map stored in a memory in loading units according to a loading order, storing, by a buffer controller, the loaded input data in a reuse buffer of an address rotationally allocated according to the loading order, and transmitting, by each of a plurality of senders, to an executer respective input data corresponding to each output data of respective convolution operations among the input data stored in the reuse buffer, wherein portions of the transmitted respective input data overlap other.

Computing method and device with data sharing

A method of processing data in a neural network, includes identifying a sparsity of input data, based on valid information included in the input data in which the input data includes valid values and invalid values, generate rearranged input data, based on a form of the sparsity by rearranging, in the input data, location of at least one of the valid values and the invalid values, and generating, by performing a convolution on the rearranged input data in the neural network, an output.

Method and apparatus for processing data

A data transmission method for a convolution operation, and a convolution operation apparatus including a fetcher that includes a loader, at least one sender, a buffer controller, and a reuse buffer. The method includes loading, by the loader, input data of an input feature map according to a loading order, based on input data stored in the reuse buffer, a shape of a kernel to be used for a convolution operation, and two-dimensional (2D) zero-value information of weights of the kernel; storing, by the buffer controller, the loaded input data in the reuse buffer of an address cyclically assigned according to the loading order; and selecting, by each of the at least one sender, input data corresponding to each output data of a convolution operation among the input data stored in the reuse buffer, based on one-dimensional (1D) zero-value information of the weights, and outputting the selected input data.

Data transmission method for convolution operation, fetcher, and convolution operation apparatus

A processor-implemented neural network method includes: generating a bit vector based on whether each of a plurality of input activations within a neural network is 0; merging the bit vector into the input activations such that bit values within the neural network included in the bit vector are most significant bits (MSBs) of multi bit expressions of the input activations; merging the bit vector into weights such that the bit values included in the bit vector are MSBs of multi bit expressions of the weights; sorting the input activations and the weights based on bits corresponding to the MSBs; and implementing the neural network, including performing operations between the sorted input activations and the sorted weights.

Method and apparatus with neural network operation

An electronic device includes a housing including a first plate, a second plate facing away from the first plate, and a lateral member surrounding a space between the first plate and the second plate; a display visible through at least part of the first plate; and a glass construction constructing at least part of the second plate. The glass construction includes a glass plate including a first face outwardly facing the housing and a second face facing away from the first face, an inorganic layer including a first roughness and constructed on the first face, a first polymer layer disposed between the first plate and the second face, an Optically Clear Adhesive (OCA) layer disposed between the second face and the first polymer layer, and a second polymer layer disposed between the first plate and the first polymer layer and including a third face and a fourth face.

Electronic device having housing

An electronic device including a housing, a display, an adhesive layer, a first decoration layer, and a second decoration layer. The housing includes a front plate, a rear plate, and a lateral member surrounding a space between the front and rear plates. The display is viewed through at least a portion of the front plate. The adhesive layer is combined with one of the front and rear plates. The first decoration layer includes a first shape-cured layer and a first color layer. The first shape-cured layer is combined with the adhesive layer, has a first three-dimensional pattern, and is cured by an external stimulus. The second decoration layer includes a second shape-cured layer and a second color layer. The second shape-cured layer is combined with the first color layer, has a second three-dimensional pattern, and is cured by an external stimulus.

Decoration film and electronic device including the same

Growing community of inventors

Suwon-si, South Korea

Yoojin Kim