High-Performance and CMOS-Compatible Electrochemical Random Access Memory For Neuromorphic Computing

用于神经形态计算的高性能且 CMOS 兼容的电化学随机存取存储器

• 批准号: 1950182
• 负责人: Qing Cao
• 金额: $ 42万
• 依托单位: University of Illinois at Urbana-Champaign
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-03-15 至 2023-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1950182&HistoricalAwards=false
• 关键词: Performance; CMOS; Compatible; Electrochemical; Random

Artificial intelligence has made phenomenal progress in recent years. It is having a remarkable social impact with emerging applications such as face recognition and self-driving cars. However, such improvement comes with the cost of aggressively increased depth and size of the deep neural network models utilized, which leads to exponentially increasing computational load. This poses significant challenges for hardware implementations in terms of computation, memory, and communication resources. The objective of this project is to develop the next-generation neuro-inspired deep-learning hardware, which has potential to perform the data-intensive computation required by the artificial-intelligence algorithms with thousands times higher energy efficiency, compared to what is possible using current silicon complementary metal-oxide-semiconductor technology. The educational goal is to sustain STEM workforce pipeline development by exploiting the outreach opportunities and knowledge generated in the proposed project. Efforts will be to establish hands-on module for K-6 students to learn the difference between computer-based expert system and the human/machine learning process, as well as the working principles of artificial synapses for neuromorphic computing, with the purpose of introducing engineering to them. At the undergraduate level, PI proposes to incorporate case-analysis in engineering class, by capitalizing on PI’s industrial experiences. The target will be to help students develop the capability of using engineering judgement in decision-making regarding realistic technology development problems, which will have direct connection to what they learn in classroom.To achieve this objective, new types of high-performance and silicon complementary metal-oxide-semiconductor compatible electrochemical random access memories will be designed, fabricated, characterized, and optimized. These devices can serve as multi-level artificial synapses with near-symmetric weight update in response to pulsed input to dramatically accelerate the online training and the inference of deep neural networks. More specifically, two novel device prototypes will be explored in parallel during the grant term: one operates based on the resistance switch in a functional oxide channel modulated by the gate-controlled reversible insertion of protons from oxides with high ionic conductivity; the other is based on the resistance switch in multilayered two-dimensional semiconductors modulated by the gate-controlled intercalation of copper ions from fast ion-transporting metal-chalcogenide glass. A symmetric gate-channel stack will be adopted to minimize the drift of the device open-circuit potential during operation. The scientific goal of this project is to elucidate the correlation between the intercalant types, properties of the corresponding solid-state electrolytes and the intercalatable channels, device dimensions, and the electrochemical random access memory performance, using a combination of experiment and physics-driven device modeling. The technological goal is to move electrochemical random access memory from initial proof-of-concept demonstrations to a practical technology. Material innovations will firstly be applied on all the components across the device gate-channel stack to drastically enhance their performance, especially the device speed, retention, and endurance. Individual memory cells with sub-100 nm dimensions and 3 by 3 pseudo-crossbar arrays will then be demonstrated. These efforts will help us assess the technological promise of electrochemical random access memory, especially their ultimately achievable speed and their scalability into both nanoscale devices and large-scale integrated arrays.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

近年来，人工智能在人脸识别和自动驾驶汽车等新兴应用中取得了显着的社会影响，然而，这种进步伴随着深度神经网络模型深度和规模的大幅增加。这给硬件实现带来了计算、内存和通信资源方面的巨大挑战，该项目的目标是开发下一代神经启发的深度学习硬件。执行数据密集型任务的潜力与当前硅互补金属氧化物半导体技术相比，人工智能算法所需的计算具有数千倍的能源效率，教育目标是通过利用外展机会和产生的知识来维持 STEM 劳动力管道的发展。拟议的项目将致力于为 K-6 学生建立实践模块，以了解基于计算机的专家系统和人类/机器学习过程之间的区别，以及用于神经形态计算的人工突触的工作原理，为了向本科生介绍工程知识，PI 建议利用 PI 的行业经验，在工程课程中纳入案例分析，目标是帮助学生培养在决策中运用工程判断的能力。关于现实的技术开发问题，这将与他们在课堂上学到的知识有直接联系。为了实现这一目标，将设计、制造、表征新型高性能和硅互补金属氧化物半导体兼容的电化学随机存取存储器，并进行了优化。可以作为多级人工突触，具有近对称权重更新，以响应脉冲输入，从而显着加速深度神经网络的在线训练和推理。更具体地说，将在资助期内并行探索两种新颖的设备原型：一种是基于功能氧化物通道中的电阻开关，该电阻开关是通过从具有高离子电导率的氧化物中门控可逆插入质子来调制的；另一种是基于多层二维半导体中的电阻开关，该电阻开关是由高离子电导率的氧化物调制的。该项目的科学目标是阐明快速离子传输金属硫族化物玻璃中铜离子的栅极控制嵌入，以最大限度地减少器件开路电位的漂移。结合实验和物理驱动的器件建模，研究插入剂类型、相应固态电解质的性质和可插入通道、器件尺寸和电化学随机存取存储器性能之间的相关性。将电化学随机存取存储器从最初的概念验证演示转变为实用技术，材料创新将首先应用于器件栅极通道堆栈中的所有组件，以显着提高其性能，特别是器件速度、保持力和稳定性。然后将展示具有亚 100 nm 尺寸和 3 x 3 伪交叉阵列的单个存储单元，这些努力将帮助我们评估电化学随机存取存储器的技术前景，特别是它们最终可实现的速度和纳米级的可扩展性。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

CMOS-compatible electrochemical synaptic transistor arrays for deep learning accelerators

用于深度学习加速器的 CMOS 兼容电化学突触晶体管阵列

• DOI: 10.1038/s41928-023-00939-7
• 发表时间: 2023-03-27
• 期刊: Nature Electronics
• 影响因子: 34.3
• 作者: Jinsong Cui;Fufei An;Jiangchao Qian;Yuxuan Wu;Luke L. Sloan;Saran Pidaparthy;J. Zuo;Qing Cao
• 通讯作者: Qing Cao

Carbon nanotube transistor technology for More-Moore scaling

用于摩尔-摩尔缩放的碳纳米管晶体管技术

• DOI: 10.1007/s12274-021-3459-z
• 发表时间: 2021-04-26
• 期刊: Nano Research
• 影响因子: 9.9
• 作者: Q. Cao