Collaborative Research: MLWiNS: Hyperdimensional Computing for Scalable IoT Intelligence Beyond the Edge

协作研究：MLWiNS：用于超越边缘的可扩展物联网智能的超维计算

• 批准号: 2003277
• 负责人: Baris Aksanli
• 金额: $ 6万
• 依托单位: San Diego State University Foundation
• 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: 2020-07-01 至 2023-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2003277&HistoricalAwards=false
• 关键词: Collaborative; Research; MLWiNS; Hyperdimensional; Computing

The Internet of Things (IoT) generates large amounts of data that machine learning algorithms today process in the cloud. The heterogeneity of the data types and devices, along with limited computing and communication capabilities of IoT devices, poses a significant challenge to real-time training and learning with classical machine learning algorithms. This project instead proposes to use Hyperdimensional (HD) computing for distributed machine learning. HD computing is a brain-inspired machine learning paradigm that transforms data into knowledge at very low cost, while being extremely robust to errors. When completed, this project has the potential to change the way machine learning is done today – instead of depending on the cloud, IoT systems will be able to make quality decisions on the spot, in real time, regardless of connectivity, with long battery lifetime. This will be made possible by designing: i) novel HD encoding schemes to represent various data in IoT applications including numerical feature vectors, time-series data, and images, ii) a novel distributed learning framework for IoT networks by incorporating active learning to considerably reduce communication overhead and learning costs, and iii) a reliable learning solution based on the error-tolerant characteristic of HD computing. The ideas developed in this project will be tested on both UCSD and SDSU using a fully instrumented testbed for human activity recognition.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.

物联网（IoT）生成了大量的数据，这些数据是在云中进行机器学习算法的大量数据。数据类型和设备的异质性以及物联网设备的计算和通信功能有限，对实时培训和通过古典机器学习算法提出了重大挑战。相反，该项目建议使用高维（HD）计算进行分布式机器学习。高清计算是一种受脑启发的机器学习范式，可将数据以非常低的成本转换为知识，同时对错误非常强大。完成后，该项目有可能改变今天的机器学习方式 - 而不是依赖云，而是物联网系统将能够实时做出优质决策，无论连接性如何，电池寿命很长。设计将通过：i）新颖的高清编码方案来代表物联网应用程序中的各种数据，包括数值功能矢量，时间序列数据和图像，ii）一个新型的分布式学习框架，通过将主动学习转换为有力地减少沟通开销和学习成本，以及III的可靠学习解决方案，以及ii）基于错误控制HD的可靠学习解决方案。该项目中开发的思想将在UCSD和SDSU上使用经过完整的人类活动识别测试的仪器进行测试。该奖项反映了NSF的法定任务，并通过使用基金会的知识分子和更广泛的影响审查标准来评估NSF的法定任务。

项目成果

Multi-label HD Classification in 3D Flash

• DOI: 10.1109/vlsi-soc46417.2020.9344070
• 发表时间: 2020-10
• 期刊: 2020 IFIP/IEEE 28th International Conference on Very Large Scale Integration (VLSI-SOC)
• 作者: Justin Morris;Yilun Hao;Saransh Gupta;R. Ramkumar;Jeffrey Yu;M. Imani;Baris Aksanli;Tajana Simunic

HD2FPGA: Automated Framework for Accelerating Hyperdimensional Computing on FPGAs

HD2FPGA：加速 FPGA 上超维计算的自动化框架

• DOI: 10.1109/isqed57927.2023.10129332
• 发表时间: 2023
• 期刊: 2023 24th International Symposium on Quality Electronic Design (ISQED
• 作者: Zhang, Tinaqi;Salamat, Sahand;Khaleghi, Behnam;Morris, Justin;Aksanli, Baris;Rosing, Tajana Simunic
• 通讯作者: Rosing, Tajana Simunic

AdaptBit-HD: Adaptive Model Bitwidth for Hyperdimensional Computing

AdaptBit-HD：超维计算的自适应模型位宽

• DOI: 10.1109/iccd53106.2021.00026
• 发表时间: 2021
• 期刊: The 39th IEEE International Conference on Computer Design
• 作者: Morris, J.

HyDREA: Towards More Robust and Efficient Machine Learning Systems with Hyperdimensional Computing

HyDREA：通过超维计算实现更强大、更高效的机器学习系统

• DOI: 10.23919/date51398.2021.9474218
• 发表时间: 2021
• 期刊: Automation & Test in Europe Conference & Exhibition (DATE
• 作者: Morris, J.

Adversarial-HD: Hyperdimensional Computing Adversarial Attack Design for Secure Industrial Internet of Things

• DOI: 10.1145/3576914.3587484
• 发表时间: 2023-05
• 期刊: Proceedings of Cyber-Physical Systems and Internet of Things Week 2023
• 作者: Onat Gungor;T. Rosing;Baris Aksanli