SPX: Collaborative Research: Ula! - An Integrated Deep Neural Network (DNN) Acceleration Framework with Enhanced Unsupervised Learning Capability

SPX：合作研究：乌拉！

• 批准号: 1725456
• 负责人: Yiran Chen
• 金额: $ 52万
• 依托单位: Duke University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-01 至 2022-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1725456&HistoricalAwards=false
• 关键词: SPX; Collaborative; Research; Ula; Integrated

In light of very recent revolutions of unsupervised learning algorithms (e.g., generative adversarial networks and dual-learning) and the emergence of their applications, three PIs/co-PI from Duke and UCSB form a team to design Ula! - an integrated DNN acceleration framework with enhanced unsupervised learning capability. The project revolutionizes the DNN research by introducing an integrated unsupervised learning computation framework with three vertically-integrated components from the aspects of software (algorithm), hardware (computing), and application (realization). The project echoes the call from the BRAIN Initiative (2013) and the Nanotechnology-Inspired Grand Challenge for Future Computing (2015) from the White House. The research outcomes will benefit both Computational Intelligence (CI) and Computer Architecture (CA) industries at large by introducing a synergy between computing paradigm and artificial intelligence (AI). The corresponding education components  enhance existing curricula and pedagogy by introducing interdisciplinary modules on the software/hardware co-design for AI with creative teaching practices, and give special attentions to women and underrepresented minority groups.The project performs three tasks: (1) At the software level, a generalized hierarchical decision-making (GHDM) system is designed to efficiently execute the state-of-the-art unsupervised learning and reinforcement learning processes with substantially reduced computation cost; (2) At the hardware level, a novel DNN computing paradigm is designed with enhanced unsupervised learning supports, based on the novelties in near data computing, GPU architecture, and FGPA + heterogeneous platforms; (3) At the application level, the usage of Ula! is exploited in scenarios that can greatly benefit from unsupervised learning and reinforcement learning. The developed techniques are also demonstrated and evaluated on three representative computing platforms: GPU, FPGA, and emerging nanoscale computing systems, respectively.

鉴于最近无监督学习算法的革命（例如，生成对抗网络和双重学习）及其应用的出现，来自杜克大学和UCSB的三位pi /co-PI组成了一个团队来设计Ula！-集成深度神经网络加速框架，增强无监督学习能力。该项目通过引入一个集成的无监督学习计算框架，从软件（算法）、硬件（计算）和应用（实现）三个方面垂直集成的组件，彻底改变了深度神经网络的研究。该项目响应了白宫2013年发起的“大脑计划”（BRAIN Initiative）和2015年发起的“纳米技术激发的未来计算大挑战”（Nanotechnology-Inspired Grand Challenge for Future Computing）的号召。研究成果将通过引入计算范式和人工智能（AI）之间的协同作用，使计算智能（CI）和计算机架构（CA）行业受益。相应的教育组成部分通过引入人工智能软件/硬件协同设计的跨学科模块，以创造性的教学实践来加强现有的课程和教学法，并特别关注妇女和代表性不足的少数群体。该项目完成了三个任务：(1)在软件层面，设计了一个广义分层决策（GHDM）系统，以有效地执行最先进的无监督学习和强化学习过程，大大降低了计算成本；(2)在硬件层面，基于近数据计算、GPU架构和FGPA +异构平台的新颖性，设计了一种具有增强无监督学习支持的新型深度神经网络计算范式；(3)在应用程序层面，Ula！在可以从无监督学习和强化学习中获益的场景中被利用。所开发的技术还分别在三个代表性的计算平台上进行了演示和评估：GPU、FPGA和新兴的纳米级计算系统。

项目成果

MobiEye: An Efficient Cloud-based Video Detection System for Real-Time Mobile Applications

• DOI: 10.1145/3316781.3317865
• 发表时间: 2019-06
• 期刊: 2019 56th ACM/IEEE Design Automation Conference (DAC)
• 作者: Jiachen Mao;Qing Yang;Ang Li;H. Li;Yiran Chen

PENNI: Pruned Kernel Sharing for Efficient CNN Inference

• 发表时间: 2020-05
• 期刊: ArXiv
• 作者: Shiyu Li;Edward Hanson;H. Li;Yiran Chen

Reshaping Future Computing Systems With Emerging Nonvolatile Memory Technologies

利用新兴非易失性内存技术重塑未来计算系统

• DOI: 10.1109/mm.2018.2885588
• 发表时间: 2019
• 期刊: IEEE Micro
• 影响因子: 3.6
• 作者: Chen, Yiran

AdaLearner: An adaptive distributed mobile learning system for neural networks

AdaLearner：神经网络的自适应分布式移动学习系统

• DOI: 10.1109/iccad.2017.8203791
• 发表时间: 2017
• 期刊: IEEE/ACM International Conference on Computer-Aided Design (ICCAD
• 作者: Mao, Jiachen;Qin, Zhuwei;Xu, Zirui;Nixon, Kent W.;Chen, Xiang;Li, Hai;Chen, Yiran
• 通讯作者: Chen, Yiran

Neuromorphic Computing Systems: From CMOS To Emerging Nonvolatile Memory

• DOI: 10.2197/ipsjtsldm.12.53
• 发表时间: 2019
• 期刊: IPSJ Trans. Syst. LSI Des. Methodol.
• 作者: Chaofei Yang;Ximing Qiao;Yiran Chen