Material and Device Building Blocks for Hardware Acceleration of Machine Learning and Artificial Intelligence Algorithms
用于机器学习和人工智能算法硬件加速的材料和设备构建模块
基本信息
- 批准号:2004791
- 负责人:
- 金额:$ 35万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2020
- 资助国家:美国
- 起止时间:2020-07-15 至 2024-06-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Non-technical description: Artificial intelligence (AI) algorithms have emerged as key drivers of technology and innovation. These algorithms enable large amounts of data to be distilled down to valuable insights. Nearly all industries have been transformed by these technologies, and new industries only possible due to these technologies are emerging. Unfortunately, the general-purpose hardware that enabled the past 50 years of computing is fundamentally unsuited to run AI algorithms efficiently. This research focuses on developing material growth techniques and specialized devices specifically tailored to addressing the needs of next generation computing algorithms. The outcome of this research is materials and devices that can be integrated directly with traditional hardware to improve the performance of AI with respect to speed and power. Thus, the results of this work can impact a wide variety of fields, ranging from semiconductors to self-driving cars. Graduate students working on this project are trained in materials, devices, and algorithms for AI, a critical need for the workforce of the future. Activities to bolster high school students’ math and science skills are incorporated to encourage their interest in science and engineering related fields. A focus of these activities is the inclusion of underrepresented groups. The results of this research are published in journals, presented at conferences, and incorporated into both undergraduate and graduate level classes.Technical description: The primary goal of this project is to utilize crystalline III-V semiconductors on amorphous substrates as the material and device building blocks for future generations of neuromorphic processors. Neuromorphic computing architectures and systems have the potential to rapidly generate insight from massive datasets with very-low power compared to current von Neumann processor architectures. However, current implementations of analog accelerators based on non-volatile memory elements exhibit unacceptably low classification accuracy on model problems. Additionally, artificial neural network architectures still exhibit ~6-8 orders of magnitude greater energy consumption as compared to the brain. Here, an algorithm driven approach is used to design devices for artificial neural network and spiking neural network accelerators. These devices are fabricated and characterized using III-V high-mobility channels directly grown on amorphous substrates below 400 oC, enabling CMOS back-end integration compatibility. First, the performance limits of III-V’s grown on amorphous substrates are identified. Next, memory devices for artificial neural network synapses are designed, fabricated and characterized. Finally, spiking synaptic devices—artificial devices which mimic biological synapses are explored. The results of this work have the potential to enable specialized hardware for AI to be fabricated directly on traditional processors impacting all areas that presently utilize AI.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.
非技术描述:人工智能(AI)算法已成为技术和创新的关键驱动力。这些算法能够将大量数据提炼为有价值的见解。几乎所有的行业都被这些技术所改变,而只有这些技术才可能出现的新行业正在出现。不幸的是,过去50年来支持计算的通用硬件从根本上不适合有效地运行AI算法。这项研究的重点是开发材料生长技术和专门针对下一代计算算法需求的专用设备。这项研究的成果是可以直接与传统硬件集成的材料和设备,以提高人工智能在速度和功率方面的性能。因此,这项工作的结果可能会影响从半导体到自动驾驶汽车等各种领域。从事该项目的研究生接受人工智能材料、设备和算法的培训,这是未来劳动力的关键需求。加强高中生数学和科学技能的活动被纳入,以鼓励他们对科学和工程相关领域的兴趣。这些活动的一个重点是纳入代表性不足的群体。本研究的结果发表在期刊上,在会议上发表,并纳入本科生和研究生水平的classes.Technical描述:本项目的主要目标是利用非晶衬底上的晶体III-V半导体作为未来几代神经形态处理器的材料和器件构建块。与当前的冯·诺依曼处理器架构相比,神经形态计算架构和系统具有以非常低的功率从海量数据集快速生成洞察力的潜力。然而,基于非易失性存储器元件的模拟加速器的当前实现在模型问题上表现出不可接受的低分类精度。此外,与大脑相比,人工神经网络架构仍然表现出约6-8个数量级的能量消耗。在这里,算法驱动的方法是用来设计人工神经网络和尖峰神经网络加速器的设备。这些器件采用直接在400 oC以下的非晶衬底上生长的III-V族高迁移率沟道制造和表征,实现了CMOS后端集成兼容性。首先,III-V族的非晶衬底上生长的性能限制被确定。接下来,设计、制造和表征用于人工神经网络突触的存储器装置。最后,探讨了模拟生物突触的人工突触装置-尖峰突触装置。这项工作的结果有可能使人工智能的专用硬件直接在传统处理器上制造,影响目前使用人工智能的所有领域。该奖项反映了NSF的法定使命,并通过使用基金会的知识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
期刊论文数量(1)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Machine Vision with InP based Floating-gate Photo-field-effective Transistors for Color-mixed Image Recognition
采用基于 InP 的浮栅光场有效晶体管的机器视觉,用于混色图像识别
- DOI:10.1109/jqe.2022.3169565
- 发表时间:2022
- 期刊:
- 影响因子:2.5
- 作者:Tao, Jun;Vazquez, Juan Sanchez;Chae, Hyun Uk;Ahsan, Ragib;Kapadia, Rehan
- 通讯作者:Kapadia, Rehan
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Rehan Kapadia其他文献
Challenges and prospects of nanopillar-based solar cells
- DOI:
10.1007/s12274-009-9091-y - 发表时间:
2009-11-01 - 期刊:
- 影响因子:9.000
- 作者:
Zhiyong Fan;Daniel J. Ruebusch;Asghar A. Rathore;Rehan Kapadia;Onur Ergen;Paul W. Leu;Ali Javey - 通讯作者:
Ali Javey
Rehan Kapadia的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Rehan Kapadia', 18)}}的其他基金
Heterogeneous III-V CMOS on Si via Direct Growth
通过直接生长在 Si 上实现异质 III-V CMOS
- 批准号:
1610604 - 财政年份:2016
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
相似海外基金
Building a microfluidic device to mimic the peritoneal cavity
构建模拟腹膜腔的微流体装置
- 批准号:
574766-2022 - 财政年份:2022
- 资助金额:
$ 35万 - 项目类别:
University Undergraduate Student Research Awards
CAREER: Quantum Spintronic Device Building Blocks with Magnetically Ordered Materials
职业:采用磁有序材料的量子自旋电子器件构建块
- 批准号:
2246254 - 财政年份:2022
- 资助金额:
$ 35万 - 项目类别:
Continuing Grant
CAREER: Quantum Spintronic Device Building Blocks with Magnetically Ordered Materials
职业:采用磁有序材料的量子自旋电子器件构建模块
- 批准号:
1941426 - 财政年份:2020
- 资助金额:
$ 35万 - 项目类别:
Continuing Grant
Creating a Building Code for Medical Device Software Security
创建医疗设备软件安全构建代码
- 批准号:
1452113 - 财政年份:2014
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
SBIR Phase II: Through-Building Device-free Localization for Emergency and Tactical Operations
SBIR 第二阶段:用于紧急和战术行动的贯穿建筑的无设备定位
- 批准号:
1256633 - 财政年份:2013
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
EVALUATION OF SEISMIC PERFORMANCE INDEX AND EFFECT OF RETROFITTING BY ENERGY DISSIPATION DEVICE ON EXISTING HIGH-RISE RC BUILDING DUE TO CYCLIC DEFORMATIONS
既有高层钢筋混凝土建筑循环变形抗震性能指标评价及消能装置改造效果
- 批准号:
25420569 - 财政年份:2013
- 资助金额:
$ 35万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
SBIR Phase I: Through-Building Device-free Localization for Emergency and Tactical Operations
SBIR 第一阶段:针对紧急和战术行动的贯穿建筑的无设备定位
- 批准号:
1142493 - 财政年份:2012
- 资助金额:
$ 35万 - 项目类别:
Standard Grant
SEISMIC PERFORMANCE INDEX AND EFFECT OF RETROFITTING BY ENERGY DISSIPATION DEVICE ON EXISTING HIGH-RISE RC BUILDING
既有高层钢筋混凝土建筑抗震性能指标及消能装置改造效果
- 批准号:
22560556 - 财政年份:2010
- 资助金额:
$ 35万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Study on type of traditional technique and device of innovative technique in conservation of the wooden building
木结构建筑保护传统技术类型及创新技术装置研究
- 批准号:
21500986 - 财政年份:2009
- 资助金额:
$ 35万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Designing and Building a Pneumatic Loading Device for Pure Deviatoric Loading of Sols
设计和构建用于溶胶纯偏向加载的气动加载装置
- 批准号:
6426415 - 财政年份:1964
- 资助金额:
$ 35万 - 项目类别: