E2CDA: Type I: Collaborative Research: Energy Efficient Learning Machines (ENIGMA)
E2CDA:类型 I:协作研究:节能学习机 (ENIGMA)
基本信息
- 批准号:1640078
- 负责人:
- 金额:$ 67.85万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2016
- 资助国家:美国
- 起止时间:2016-09-01 至 2021-08-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
The project will aim to develop computing hardware and software that improve the energy efficiency of learning machines by many orders of magnitude. In doing so it will enable large societal adoption of such machines, paving the way for new applications in diverse areas such as manufacturing, healthcare, agriculture, and many others. For example, machines that learn the behavioral trends of individual human beings by collecting data from myriads of sensors may be able to design the most appropriate drugs. Similarly, one may envision machines that learn trends in the weather and thereby assist in predicting the most optimized preparations for the next crop cycle. The possibilities are literally endless. However, the canonical learning machines of today need huge amount of energy, significantly hindering their adoption for widespread applications. The goal of this project will be to explore, evaluate and innovate new hardware and software paradigms that could reduce energy dissipation in learning machines by a significant amount. The team of researchers consists of experts in mathematics, neuroscience, electronic devices and materials and computer circuit and system design that will foster a unique platform for both innovative research and interdisciplinary training of graduate students.We are witnessing a regimental shift in the computing paradigm. For a vast number of applications, cognitive functions such as classification, recognition, synthesis, decision-making and learning are gaining rapid importance in a world that is infused with sensing modalities, often paraphrased under a common term of "Big Data", that are in critical need of efficient information-extraction. This is in sharp contrast to the past when the central objective of computing was to perform calculations on numbers and produce results with extreme numerical accuracy. We aim to approach this problem by exploiting cognitive models that have shown efficacy in "one shot" learning. In this approach, the information is represented by means of high dimensional (HD) vectors. These vectors follow a set of predetermined mathematical operations that ensure that the resulting vector after such operations is unique. The uniqueness can in turn be used as "learning" and the predefined nature of mathematical operations make the learning "one shot". When paired with traditional artificial neural network or deep learning algorithms, such "one shot" learning could significantly reduce the number of necessary computing operations, leading to orders of magnitude reduction in energy dissipation. We shall explore the entire computer hierarchy, staring from materials and devices, all the way up to system design and optimization to exploit the unique capabilities afforded by the HD computing, with the ultimate objective of realizing energy efficient learning machines (ENIGMA).
该项目旨在开发计算硬件和软件,将学习机器的能源效率提高许多数量级。通过这样做,它将使这种机器的大规模社会采用成为可能,为制造业、医疗保健、农业等许多领域的新应用铺平道路。例如,通过从无数传感器收集数据来学习人类个体行为趋势的机器可能能够设计出最合适的药物。类似地,人们可以设想机器学习天气趋势,从而帮助预测下一个作物周期的最优化准备。可能性简直是无穷无尽的。然而,今天的规范学习机器需要大量的能量,这大大阻碍了它们的广泛应用。该项目的目标是探索、评估和创新新的硬件和软件范例,以显著降低学习机器的能耗。研究团队由数学、神经科学、电子设备和材料以及计算机电路和系统设计方面的专家组成,将为研究生的创新研究和跨学科培训提供一个独特的平台。我们正在见证计算范式的军团式转变。对于大量的应用程序,认知功能,如分类,识别,综合,决策和学习正在获得快速的重要性,在一个充满了感测模式的世界,通常在一个共同的术语下解释为“大数据”,这是迫切需要有效的信息提取。这与过去形成了鲜明的对比,当时计算的中心目标是对数字进行计算,并产生具有极高数值精度的结果。我们的目标是通过利用在“一次性”学习中表现出功效的认知模型来解决这个问题。在这种方法中,信息是由高维(HD)向量的手段。这些向量遵循一组预定的数学运算,这些运算确保在这些运算之后得到的向量是唯一的。这种唯一性可以反过来被用作“学习”,而数学运算的预定义性质使得学习“一次性”。当与传统的人工神经网络或深度学习算法配对时,这种“一次性”学习可以显著减少必要的计算操作的数量,从而导致能量耗散的数量级减少。我们将探索整个计算机层次结构,从材料和设备开始,一直到系统设计和优化,以利用HD计算提供的独特功能,最终目标是实现节能学习机器(ENIGMA)。
项目成果
期刊论文数量(2)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Illusion of large on-chip memory by networked computing chips for neural network inference
- DOI:10.1038/s41928-020-00515-3
- 发表时间:2021-01
- 期刊:
- 影响因子:34.3
- 作者:R. Radway;Andrew Bartolo;Paul C. Jolly;Zainab F. Khan;B. Le;Pulkit Tandon;Tony F. Wu;Yunfeng Xin;E. Vianello;P. Vivet;E. Nowak;H. Wong;M. Aly;E. Beigné;Mary Wootters;S. Mitra
- 通讯作者:R. Radway;Andrew Bartolo;Paul C. Jolly;Zainab F. Khan;B. Le;Pulkit Tandon;Tony F. Wu;Yunfeng Xin;E. Vianello;P. Vivet;E. Nowak;H. Wong;M. Aly;E. Beigné;Mary Wootters;S. Mitra
Brain-inspired computing exploiting carbon nanotube FETs and resistive RAM: Hyperdimensional computing case study
- DOI:10.1109/isscc.2018.8310399
- 发表时间:2018-02
- 期刊:
- 影响因子:0
- 作者:Tony F. Wu;Haitong Li;Ping-Chen Huang;Abbas Rahimi;J. Rabaey;H. Wong;M. Shulaker;S. Mitra
- 通讯作者:Tony F. Wu;Haitong Li;Ping-Chen Huang;Abbas Rahimi;J. Rabaey;H. Wong;M. Shulaker;S. Mitra
{{
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 }}
Subhasish Mitra其他文献
Dendrite-inspired Computing to Improve Resilience of Neural Networks to Faults in Emerging Memory Technologies
树突启发计算可提高神经网络对新兴内存技术故障的恢复能力
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:0
- 作者:
L. K. John;F. M. G. França;Subhasish Mitra;Zachary Susskind;P. M. V. Lima;Igor D. S. Miranda;E. B. John;Diego L. C. Dutra;M. Breternitz - 通讯作者:
M. Breternitz
Segregation of a Phosphorus Rich Phase During Differential Solidification of BOF Slag
- DOI:
10.1007/s11663-022-02586-3 - 发表时间:
2022-07-06 - 期刊:
- 影响因子:3.100
- 作者:
Thi Bang Tuyen Nguyen;Subhasish Mitra;Geoffrey M. Evans;Hamid Doostmohammadi;Brian J. Monaghan;Paul Zulli;Kyoung-oh Jang;Damien O’Dea;Tom Honeyands - 通讯作者:
Tom Honeyands
Measurement of gas dispersion parameters in a reflux flotation cell
回流浮选槽中气体分散参数的测量
- DOI:
10.1016/j.mineng.2025.109526 - 发表时间:
2025-10-01 - 期刊:
- 影响因子:5.000
- 作者:
Abdullaziz Glabe Zakari;Raju Chowdhury;Peter Ireland;Geoffrey Evans;Subhasish Mitra - 通讯作者:
Subhasish Mitra
Effect of bubble surface loading on bubble rise velocity
- DOI:
10.1016/j.mineng.2021.107252 - 发表时间:
2021-12-01 - 期刊:
- 影响因子:
- 作者:
Ai Wang;Mohammad Mainul Hoque;Roberto Moreno-Atanasio;Elham Doroodchi;Geoffrey Evans;Subhasish Mitra - 通讯作者:
Subhasish Mitra
Cooling future system-on-chips with diamond inter-tiers
使用金刚石中间层冷却未来片上系统
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:8.9
- 作者:
M. Malakoutian;Anna Kasperovich;Dennis Rich;Kelly Woo;Christopher Perez;R. Soman;Devansh Saraswat;Jeong;Maliha Noshin;Michelle Chen;Sam Vaziri;Xinyu Bao;Che Chi Shih;W. Woon;M. Asheghi;Kenneth E. Goodson;S. Liao;Subhasish Mitra;Srabanti Chowdhury - 通讯作者:
Srabanti Chowdhury
Subhasish Mitra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('Subhasish Mitra', 18)}}的其他基金
Collaborative Research: SHF: Small: Quasi Weightless Neural Networks for Energy-Efficient Machine Learning on the Edge
合作研究:SHF:小型:用于边缘节能机器学习的准失重神经网络
- 批准号:
2326895 - 财政年份:2023
- 资助金额:
$ 67.85万 - 项目类别:
Standard Grant
FuSe-TG: The Future of Semiconductor Technologies for Computing through Device-Architecture-Application Co-Design
FuSe-TG:通过设备-架构-应用协同设计进行计算的半导体技术的未来
- 批准号:
2235329 - 财政年份:2023
- 资助金额:
$ 67.85万 - 项目类别:
Standard Grant
Collaborative Research: Visual Cortex on Silicon
合作研究:硅上视觉皮层
- 批准号:
1317470 - 财政年份:2013
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
Workshop: Bugs and Defects in Electronic Systems: The Next Frontier
研讨会:电子系统中的错误和缺陷:下一个前沿
- 批准号:
1341270 - 财政年份:2013
- 资助金额:
$ 67.85万 - 项目类别:
Standard Grant
SHF:Medium:Collaborative Research: AgeELESS: Aging Estimation and Lifetime Enhancement in Silicon Systems
SHF:中:合作研究:AgeELESS:硅系统中的老化估计和寿命增强
- 批准号:
1161332 - 财政年份:2012
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
II-NEW: Robust Carbon Nanotube Technology for Energy-Efficient Computing Systems: A Processing and Design Infrastructure for Emerging Nanotechnologies
II-新:用于节能计算系统的稳健碳纳米管技术:新兴纳米技术的处理和设计基础设施
- 批准号:
1059020 - 财政年份:2011
- 资助金额:
$ 67.85万 - 项目类别:
Standard Grant
Collaborative Research: Variability-Aware Software for Efficient Computing with Nanoscale Devices
协作研究:利用纳米级设备进行高效计算的可变性感知软件
- 批准号:
1028831 - 财政年份:2010
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
Collaborative Research: Globally Optimized Robust Systems on Multi-Core Hardware
协作研究:多核硬件上的全局优化鲁棒系统
- 批准号:
0903459 - 财政年份:2009
- 资助金额:
$ 67.85万 - 项目类别:
Standard Grant
Collaborative Research: Design, Modeling, Automation and Experimentation of Imperfection Immune Carbon Nanotube Field Effect Transitor Circuits
合作研究:不完美免疫碳纳米管场效应晶体管电路的设计、建模、自动化和实验
- 批准号:
0702343 - 财政年份:2007
- 资助金额:
$ 67.85万 - 项目类别:
Standard Grant
相似国自然基金
铋基邻近双金属位点Type B异质结光热催化合成氨机制研究
- 批准号:
- 批准年份:2024
- 资助金额:30.0 万元
- 项目类别:省市级项目
智能型Type-I光敏分子构效设计及其抗耐药性感染研究
- 批准号:22207024
- 批准年份:2022
- 资助金额:20 万元
- 项目类别:青年科学基金项目
TypeⅠR-M系统在碳青霉烯耐药肺炎克雷伯菌流行中的作用机制研究
- 批准号:
- 批准年份:2021
- 资助金额:55 万元
- 项目类别:面上项目
替加环素耐药基因 tet(A) type 1 变异体在碳青霉烯耐药肺炎克雷伯菌中的流行、进化和传播
- 批准号:LY22H200001
- 批准年份:2021
- 资助金额:0.0 万元
- 项目类别:省市级项目
面向手性α-氨基酰胺药物的新型不对称Ugi-type 反应开发
- 批准号:LY22B020003
- 批准年份:2021
- 资助金额:0.0 万元
- 项目类别:省市级项目
BMP9/BMP type I receptors 通过激活 PPARα保护心肌梗死的机制研究
- 批准号:LQ22H020003
- 批准年份:2021
- 资助金额:0.0 万元
- 项目类别:省市级项目
C2H2-type锌指蛋白在香菇采后组织软化进程中的作用机制研究
- 批准号:32102053
- 批准年份:2021
- 资助金额:30 万元
- 项目类别:青年科学基金项目
血管阻断型Type-I光敏剂合成及其三阴性乳腺癌光诊疗
- 批准号:62120106002
- 批准年份:2021
- 资助金额:255 万元
- 项目类别:国际(地区)合作与交流项目
Chichibabin-type偶联反应在构建联氮杂芳烃中的应用
- 批准号:
- 批准年份:2020
- 资助金额:63 万元
- 项目类别:面上项目
茶尺蠖Type-II环氧性信息素合成酶关键基因的鉴定及功能研究
- 批准号:LQ21C140001
- 批准年份:2020
- 资助金额:0.0 万元
- 项目类别:省市级项目
相似海外基金
E2CDA: Type II: Collaborative Research: Metal-insulator transitions for low power switching devices
E2CDA:类型 II:协作研究:低功率开关器件的金属绝缘体转换
- 批准号:
1740213 - 财政年份:2017
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
E2CDA: Type I: Collaborative Research: Interconnects Beyond Cu
E2CDA:I 类:协作研究:铜以外的互连
- 批准号:
1740228 - 财政年份:2017
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
E2CDA: Type I: Collaborative Research: Nanophotonic Neuromorphic Computing
E2CDA:I 型:协作研究:纳米光子神经形态计算
- 批准号:
1740262 - 财政年份:2017
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
E2CDA: Type II: Collaborative Research: Metal-insulator transitions for low power switching devices
E2CDA:类型 II:协作研究:低功率开关器件的金属绝缘体转换
- 批准号:
1740119 - 财政年份:2017
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
E2CDA: Type I: Collaborative Research: Nanophotonic Neuromorphic Computing
E2CDA:I 型:协作研究:纳米光子神经形态计算
- 批准号:
1740235 - 财政年份:2017
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
E2CDA: Type I: Collaborative Research: Energy-Efficient Artificial Intelligence with Binary RRAM and Analog Epitaxial Synaptic Arrays
E2CDA:I 型:协作研究:采用二进制 RRAM 和模拟外延突触阵列的节能人工智能
- 批准号:
1740225 - 财政年份:2017
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
E2CDA: Type I: Collaborative Research: Interconnects Beyond Cu
E2CDA:I 类:协作研究:铜以外的互连
- 批准号:
1740270 - 财政年份:2017
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
E2CDA: Type II: Collaborative Research: Nanophotonic Lithium Niobate platform for next generation energy efficient and ultrahigh bandwidth optical interconnect
E2CDA:II 类:合作研究:用于下一代节能和超高带宽光学互连的纳米光子铌酸锂平台
- 批准号:
1740291 - 财政年份:2017
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
E2CDA: Type I: Collaborative Research: Energy-efficient analog computing with emerging memory devices
E2CDA:类型 I:协作研究:使用新兴存储设备的节能模拟计算
- 批准号:
1740248 - 财政年份:2017
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant
E2CDA: Type II: Collaborative Research: Nanophotonic Lithium Niobate platform for next generation energy efficient and ultrahigh bandwidth optical interconnect
E2CDA:II 类:合作研究:用于下一代节能和超高带宽光学互连的纳米光子铌酸锂平台
- 批准号:
1740296 - 财政年份:2017
- 资助金额:
$ 67.85万 - 项目类别:
Continuing Grant