RTML: Large: Efficient and Adaptive Real-Time Learning for Next Generation Wireless Systems

RTML：大型：下一代无线系统的高效、自适应实时学习

• 批准号: 1937500
• 负责人: Stratis Ioannidis
• 金额: $ 100万
• 依托单位: Northeastern University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1937500&HistoricalAwards=false
• 关键词: RTML; Large; Efficient; Adaptive; Real

Emerging wireless standards and the promise of 5G communication are driven by the need to attain faster data rates and ultra-low latency. Many incredible bleeding-edge applications, such as community/shared virtual reality experiences and self-driving cars, crucially rely on the ubiquitous availability and real-time reconfigurability of high-speed wireless links, which in turn strongly relies on the ability of next-generation wireless devices to perform a broad variety of inference tasks in real-time. The latency requirements associated with these applications imply the need for improved and accelerated machine learning through dedicated hardware. Moreover, due to the unpredictable nature of the wireless channel, inference algorithms must be able to adapt and evolve in the presence of an unfamiliar environment. This project seeks to solve this foundational challenge, with successful outcomes being able to achieve unprecedented efficiency improvements in next generation wireless systems. Ideas and findings from the project are incorporated into a number of accessible seminar talks geared at high-school and undergraduate students, to encourage further interest in engineering and science, as well as through multi-disciplinary tutorials aimed at both the wireless networking and machine learning communities.The project, executed by a multidisciplinary team of machine learning, systems, and networking researchers, advances the state of the art through novel deep learning architectures tailored to inference tasks pertinent to next generation wireless devices. It also incorporates novel model compression techniques, producing a hardware-friendly structured pruning approach for fully-connected and convolutional layers of deep neural networks, combined with a novel quantization scheme learned jointly during training. The project's quantization scheme and its hyper-parameter tuning is co-designed with an field programmable gate array (FPGA) hardware implementation and determined via deep reinforcement learning. The adaptation of parts of the network in the presence of new samples is enabled by blending lifelong learning approaches like dynamic networks and complementary learning as new objectives during training.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.

新兴的无线标准和5G通信的前景是由实现更快数据速率和超低延迟的需求驱动的。许多令人难以置信的前沿应用，如社区/共享虚拟现实体验和自动驾驶汽车，都依赖于高速无线链路的无处不在的可用性和实时可重构性，而这又严重依赖于下一代无线设备实时执行各种推理任务的能力。与这些应用程序相关的延迟要求意味着需要通过专用硬件改进和加速机器学习。 此外，由于无线信道的不可预测性，推理算法必须能够在不熟悉的环境中适应和发展。该项目旨在解决这一基本挑战，成功的结果能够在下一代无线系统中实现前所未有的效率提升。该项目的想法和发现被纳入了一些面向高中和本科生的无障碍研讨会演讲中，以鼓励对工程和科学的进一步兴趣，以及针对无线网络和机器学习社区的多学科教程。该项目由机器学习，系统和网络研究人员的多学科团队执行，通过针对与下一代无线设备相关的推理任务定制的新型深度学习架构来推进现有技术。它还结合了新的模型压缩技术，为深度神经网络的全连接和卷积层提供了一种硬件友好的结构化修剪方法，并结合了在训练过程中联合学习的新量化方案。该项目的量化方案及其超参数调整与现场可编程门阵列（FPGA）硬件实现共同设计，并通过深度强化学习确定。通过将动态网络和补充学习等终身学习方法作为培训期间的新目标，使网络的部分内容能够适应新样本。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

Pruning Adversarially Robust Neural Networks without Adversarial Examples

• DOI: 10.1109/icdm54844.2022.00120
• 发表时间: 2022-10
• 期刊: 2022 IEEE International Conference on Data Mining (ICDM)
• 作者: T. Jian;Zifeng Wang;Yanzhi Wang;Jennifer G. Dy;Stratis Ioannidis

Open-World Class Discovery with Kernel Networks

• DOI: 10.1109/icdm50108.2020.00072
• 发表时间: 2020-11
• 期刊: 2020 IEEE International Conference on Data Mining (ICDM)
• 作者: Zifeng Wang;Batool Salehi;Andrey Gritsenko;K. Chowdhury;Stratis Ioannidis;Jennifer G. Dy

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices

• DOI: 10.1007/978-3-030-58601-0_37
• 发表时间: 2020-01
• 期刊: ArXiv
• 作者: Xiaolong Ma;Wei Niu;Tianyun Zhang;Sijia Liu;Fu-Ming Guo;Sheng Lin;Hongjia Li;Xiang Chen;Jian Tang;Kaisheng Ma;Bin Ren;Yanzhi Wang

Machine Learning on Camera Images for Fast mmWave Beamforming

• DOI: 10.1109/mass50613.2020.00049
• 发表时间: 2020-12
• 期刊: 2020 IEEE 17th International Conference on Mobile Ad Hoc and Sensor Systems (MASS)
• 作者: Batool Salehi;M. Belgiovine;Saray Sanchez;Jennifer G. Dy;Stratis Ioannidis;K. Chowdhury

AirNN: Over-the-Air Computation for Neural Networks via Reconfigurable Intelligent Surfaces

• DOI: 10.1109/tnet.2022.3225883
• 发表时间: 2023-12
• 期刊: IEEE/ACM Transactions on Networking
• 作者: Sara Garcia Sanchez;Guillem Reus-Muns;Carlos Bocanegra;Yanyu Li;Ufuk Muncuk;Yousof Naderi;Yanzhi Wang;Stratis Ioannidis;K. Chowdhury