Samsung Electronics Co., Ltd.

Seoul National University

Seijoon Kim

Hyeokjun Choe

Sungroh Yoon

Seongsik Park

Hyunsoo Kim

Seungkeun Yoon

Chang-Woo Shin

Minyoung Mun

A method generates an anchor image embedding vector for an anchor image using an image representation model, determine first similarities between the anchor image and negative samples of the anchor image using first image embedding vectors for the negative samples and the generated anchor image embedding vector, determine second similarities between the anchor image and positive samples of the anchor image using second image embedding vectors for the positive samples and the generated anchor image embedding vector, obtain one of a vector corresponding to a label of the anchor image and third similarities between the label of the anchor image and labels of the negative samples, determine a loss value for the anchor image based on the determined first similarities, and the determined second similarities, and one of the obtained third similarities and a fourth similarity.

Method of training image representation model

A method of optimizing a quantization step size of an analog-to-digital converter (ADC) based on a number of crossbar arrays of a computing device includes: generating a first mapping relationship between the quantization step size of the ADC and a first root mean square error, the first root mean square error reflecting a quantization error and a clipping error, wherein the generating the first graph is based on use of only a single crossbar array; generating a second mapping relationship between the quantization step size of the ADC and a second root mean square error, the second root mean square error reflecting a quantization error, wherein the generating the second mapping is based on a uniform distribution of a total sum of quantization errors; and determining the quantization step size of the ADC based on the first mapping relationship and the second mapping relationship.

Determining quantization step size for crossbar arrays

A method of operating a storage device including a neural network processor includes outputting, by a controller device, a trigger signal instructing the neural network processor to perform a neural network operation in response to a command from a host device, requesting, by a neural network processor, target model data about parameters of a target model and instruction data for instructing the neural network operation to a memory device storing the target model data and the instruction data in response to the trigger signal, receiving, by the neural network processor, the target model data and the instruction data from the memory device and outputting, by the neural network processor, inference data based on the target model data and the instruction data.

Storage device and method of operating the same

Growing community of inventors

Seongnam-si, South Korea

Seijoon Kim