Seminar

Date 2021-05-18 
Time 16:00 
Title High-density memory for neuromorphic computing 

■ 제 목: High-density memory for neuromorphic computing 

 

 연 사: 이윤경 교수 (전북대학교 신소재공학부)              

 

■ 일 시: 2021년 5월 18(화) 오후 4시 

 

■ Host: 전석우 교수   

 

■ 참가자 접속정보 (3:50분까지 참가를 부탁드립니다)   

      접속 링크: https://kaist.zoom.us/j/8080757553 

      ID: 808 075 7553

      비밀번호: 2021mse

 

 Abstract :  

Recent advances in nanoscale resistive memory devices offer promising opportunities for in-memory computing with their capability of simultaneous information storage and processing. Crossbar arrays of the resistive memory can perform matrix-vector multiplication for data-intensive tasks, such as training and inference in machine learning. Potential utilities include the bio-inspired neuromorphic processing of data generated from mobile sensing or communication devices that requires high energy and areal efficiencies. The seminar will introduce the electrical characteristics of various chalcogenide materials, one of the most promising non-conventional memories that show both threshold and resistive switching behaviors. Atomic layer deposition of the chalcogenide materials have been developed using a new Ge(II)-guanidinate precursor to integrate three-dimensional high density memory arrays. The ALD technique enabled unique materials and device structures that improved the energy efficiencies of the chalcogenide-based memories.