公开(公告)号：US20240249150A1

公开(公告)日：2024-07-25

申请号：US18414875

申请日：2024-01-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sungwoo CHUNG ,  Younggeun KIM ,  Seunghun CHOI

IPC: G06N3/092

CPC classification number: G06N3/092

Abstract: Provided is a system configured to respectively allocate a plurality of deep neural networks to a plurality of processing units according to a particular action having maximum quality in a particular state. In addition, provided is a system configured to respectively allocate a plurality of deep neural networks to a plurality of processing units according to an action having maximum quality in a current state, and to update quality of an action selected in the current state by using a calculated reward based on a process of the plurality of deep neural networks by the allocated plurality of processing units.

公开(公告)号：US20230259422A1

公开(公告)日：2023-08-17

申请号：US18102187

申请日：2023-01-27

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITY

Inventor： Sungwoo CHUNG ,  Youngseo LEE

IPC: G06F11/10

CPC classification number: G06F11/1044

Abstract: A memory system includes a memory module and a memory controller. The memory module stores a code word group including first and second data words and a flag. The memory controller includes an error correction code (ECC) engine including a data-width aware (DWA) encoder that generates the code word group by using the first and second data words, and performs an error detection and error correction operation in one of first to third modes based on a size of each of the first and second data words, and a DWA decoder that receives the code word group, performs an error detection and error correction operation in one of the first to third modes according to a type of the code word group determined based on the flag, and extracts the first data word and the second data word from the code word group.