Collaborative Research: PPoSS: Planning: Hardware-accelerated Trustworthy Deep Neural Network

合作研究：PPoSS：规划：硬件加速的可信深度神经网络

• 批准号: 2028894
• 负责人: Xiaonan Guo
• 金额: $ 6万
• 依托单位: Indiana University
• 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: 2020-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2028894&HistoricalAwards=false
• 关键词: Collaborative; Research; PPoSS; Planning; Hardware

Deep-learning approaches have recently achieved much higher accuracy than traditional machine-learning approaches in various applications (e.g., computer vision, virtual/augmented reality, and natural language processing). Existing research has shown that large-scale data from various sources with high-resolution sensing or large-volume data-collection capabilities can significantly improve the performance of deep-learning approaches. However, state-of-the-art hardware and software cannot provide sufficient computing capabilities and resources to ensure accurate deep-learning performance in a timely manner when using extremely large-scale data. This project develops a scalable and robust heterogeneous system that includes a new low-cost, secure, deep-learning hardware-accelerator architecture and a suite of large-data-compatible deep-learning algorithms. It allows deep learning to fully benefit from extremely large-scale data and facilitates efficient, low-latency applications in connected vehicles, real-time mobile applications, and timely precision health. The new technologies resulting from this project can enable more research opportunities to design new hardware accelerators for deep learning and obtain further optimization in computational complexity and reduction in power consumption. Moreover, by integrating the research results with the undergraduate and graduate curricula and outreach activities, this project has great impacts on education and training of researchers and engineers for computer architecture, security, theory and algorithms, and systems.This project designs trustworthy hardware accelerators optimized for large-scale deep-learning computations and models the complicated structure of large-scale datasets. More specifically, this project develops a novel hardware accelerator for deep learning that can achieve low power consumption. In addition, this project designs innovative in-memory encryption schemes to secure the neural models in deep-learning accelerators. Furthermore, data-modeling and statistical-learning algorithms are developed in this project to further reduce the computing cost of deep learning when processing extremely large-scale datasets. Finally, this project builds and evaluates a prototype of the proposed heterogeneous deep-learning system in terms of efficiency, scalability, and security in multiple application domains including mobile applications, connected vehicles and precision health.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.

最近，深度学习方法在各种应用（例如计算机视觉、虚拟/增强现实和自然语言处理）中取得了比传统机器学习方法更高的准确性。现有研究表明，具有高分辨率传感或大容量数据收集能力的各种来源的大规模数据可以显着提高深度学习方法的性能。然而，最先进的硬件和软件无法提供足够的计算能力和资源来保证在使用超大规模数据时及时准确的深度学习性能。该项目开发了一个可扩展且强大的异构系统，其中包括新的低成本、安全的深度学习硬件加速器架构和一套大数据兼容的深度学习算法。它使深度学习能够充分受益于超大规模数据，并促进互联车辆、实时移动应用和及时精准健康方面的高效、低延迟应用。该项目产生的新技术可以为设计新的深度学习硬件加速器提供更多研究机会，并获得计算复杂性和功耗降低的进一步优化。此外，通过将研究成果与本科生和研究生课程以及推广活动相结合，该项目对计算机体系结构、安全、理论与算法以及系统方面的研究人员和工程师的教育和培训产生了巨大影响。该项目设计了值得信赖的优化硬件加速器用于大规模深度学习计算并对大规模数据集的复杂结构进行建模。更具体地说，该项目开发了一种新颖的深度学习硬件加速器，可以实现低功耗。此外，该项目设计了创新的内存加密方案，以保护深度学习加速器中的神经模型。此外，该项目还开发了数据建模和统计学习算法，以进一步降低深度学习在处理超大规模数据集时的计算成本。最后，该项目在移动应用、联网车辆和精准健康等多个应用领域的效率、可扩展性和安全性方面构建并评估了所提出的异构深度学习系统的原型。该奖项反映了 NSF 的法定使命，并被视为值得通过使用基金会的智力优点和更广泛的影响审查标准进行评估来支持。

项目成果

MIXP: Efficient Deep Neural Networks Pruning for Further FLOPs Compression via Neuron Bond

MIXP：高效深度神经网络修剪，通过神经元键进一步压缩 FLOP

• DOI: 10.1109/ijcnn52387.2021.9534029
• 发表时间: 2021-01
• 期刊: 2021 International Joint Conference on Neural Networks (IJCNN
• 作者: Hu, B.;Zhao, T.;Xie, Y.;Wang, Y.;Guo, X.;Cheng, J.;Chen, Y.
• 通讯作者: Chen, Y.

mmFit: Low-Effort Personalized Fitness Monitoring Using Millimeter Wave

mmFit：使用毫米波轻松进行个性化健身监测

• DOI: 10.1109/icccn54977.2022.9868878
• 发表时间: 2022-07
• 期刊: International Conference on Computer Communications and Networks (ICCCN
• 作者: Xie, Y.;Jiang, R.;Guo, X.;Wang, Y.;Cheng, J.;Chen, Y.
• 通讯作者: Chen, Y.

Universal targeted attacks against mmWave-based human activity recognition system

针对基于毫米波的人类活动识别系统的通用针对性攻击

• DOI: 10.1145/3498361.3538774
• 发表时间: 2022-06
• 期刊: Applications and Services
• 作者: Xie, Y.;Jiang, R.;Guo, X.;Wang, Y.;Cheng, J.;Chen, Y.
• 通讯作者: Chen, Y.