![第四十七讲 RRAM fabric for neuromorphic computing applications 第四十七讲 RRAM fabric for neuromorphic computing applications]()
一、讲座详情
演讲题目:RRAM fabric for neuromorphic computing applications
演讲时间:2019年6月12日9:00-10:30
演讲地点:清华大学微电子学研究所A204
主讲人: Wei D. Lu University of Michigan
二、主讲人介绍
Wei D. Lu is a Professor in the Electrical Engineering and Computer Science department at the University of Michigan, and Director of the Lurie Nano fabrication Facility. He received B.S. in physics from Tsinghua University, Beijing, China, in 1996, and Ph.D. in physics from Rice University, Houston, TX in 2003. From 2003 to 2005, he was a postdoctoral research fellow at Harvard University, Cambridge, MA. He joined the faculty of the University of Michigan in 2005. His research interest includes resistive-random access memory (RRAM), memristor-based logic circuits, neuromorphic computing systems, aggressively scaled transistor devices, and electrical transport in low-dimensional systems. To date Prof. Lu has published over 100 journal articles with 22,000 citations and h-factor of 63. He is an IEEE Fellow, a recipient of the NSF CAREER award, and co-founder and Chief Scientist of Crossbar, Inc.
卢伟博士(Wei D. Lu)是密歇根大学电子工程和计算机科学系教授,也是Lurie Nanofabrication Facility(劳瑞纳米加工装置中心)主任。他于1996年获得获得清华大学物理学学士学位,2003年在德克萨斯州休斯顿莱斯大学获得物理学博士学位。他2003年至2005年在马萨诸塞州剑桥市哈佛大学担任博士后研究员,随后加入密歇根大学。他的研究兴趣包括RRAM、基于忆阻器的逻辑电路、神经形态计算系统、大规模晶体管器件以及低维系统中的电子传输。迄今为止,卢伟教授已发表了100多篇期刊文章,引用次数达到22,000,h因子为63。他是IEEE会士,NSF CAREER奖获得者,Crossbar公司的联合创始人兼首席科学家。
三、演讲内容
Resistive random-access memory (RRAM) devices are two-terminal elements with an inherent memory effect, driven by internal ion distributions within a solid-state switching medium. As a memory device, RRAM is currently being commercialized for embedded memory and stand-alone data storage applications. RRAM crossbar networks are also widely considered as a promising candidate for future neuromorphic hardware systems due to their ability to simultaneously store weights and process information at the same physical locations. I will discuss recent progresses in RRAM devices and neuromorphic computing systems in my group, from material and device-level understandings to system-level implementations. Prototype circuits based on RRAM networks can already perform tasks such as feature extraction, data clustering and image analysis. Hybrid RRAM/CMOS integration efforts and approaches towards a general in-memory computing system will also be discussed.
阻变式存储器(RRAM)是具有记忆效应的两端元件,由固态开关介质内部的离子分布驱动。作为存储器件,RRAM既可以用于嵌入式存储器,也可以用于独立数据存储。 同时,RRAM交叉阵列网络也被广泛认为是未来实现神经形态计算的潜力硬件系统,因为它们能够在相同的物理位置同时存储权重和处理信息。此次讲座将首先介绍我的团队在RRAM器件和神经形态计算系统研究方面的最新进展,包括从材料和器件层面的机理探索到系统层面的实现。基于RRAM网络的原型电路已经可以执行诸如特征提取,数据聚类和图像分析等任务。此外,讲座还将讨论针对通用存内计算系统的混合RRAM / CMOS集成方法等。