SHF: Small: Efficient and Accurate Learning with Low-Precision Components: A Cortex-Inspired Approach

SHF：小型：使用低精度组件进行高效、准确的学习：受皮质启发的方法

• 批准号: 1715443
• 负责人: Yu Cao
• 金额: $ 45万
• 依托单位: Arizona State 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: 2017-07-15 至 2021-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1715443&HistoricalAwards=false
• 关键词: SHF; Small; Efficient; Accurate; Learning

Achieving high performance and high-energy efficiency with a small footprint is a central challenge of computer engineering. This project targets to develop technologies with cutting-edge nanoscale devices towards a self-learning chip. It will be integrated with front-end sensors, process the information in real-time, and consume ultra-low energy. The success is likely to have an impact on the society, bringing broad benefits to multiple emerging applications, mobile vision and autonomous vehicles to name a few. The interdisciplinary nature of this project, as well as the frequent interaction with industry, will provide an ideal platform for education and training of state-of-the-art science and technology. It will improve the knowledge base of intelligent system design through new curriculum development, engaging undergraduate and minority students in research and practice, and participating in outreach programs that are customized for K-12 students. Furthermore, this project will advocate the web-based interface and workshops to disseminate the latest research outcome. Microprocessors have been a ubiquitous and vitally important part in our modern-day life. However, they are facing severe issues in artificial intelligent systems, which require tremendous amount of energy and data to train and operate the sophisticated algorithm. On the contrary, animal brains at various sizes achieve remarkable feats of learning and accuracy at energy costs much lower than human-engineered systems. Therefore, the central theme of this project is to transfer the latest knowledge of the structure and function of brains into neuromorphic design, generate novel insights for improvement of the engineered system, and achieve high accuracy and high energy efficiency despite the severe precision constraints of the nanoscale components. These neurobiological principles include approximate learning rules with low-precision synapses, neural motifs of excitation and inhibition, and hierarchical network models. The goal is to accomplish complex computation with much less data volume and resources, and promise magnitudes of improvement in energy efficiency and performance than microprocessors today.

以较小的占地面积实现高性能和高能效是计算机工程的核心挑战。该项目的目标是开发具有尖端纳米级器件的技术，以实现自学习芯片。它将与前端传感器集成，实时处理信息，并且消耗超低能耗。这一成功可能会对社会产生影响，为多种新兴应用、移动视觉和自动驾驶汽车等带来广泛的好处。该项目的跨学科性质以及与行业的频繁互动将为最先进科学技术的教育和培训提供理想的平台。它将通过新课程开发、让本科生和少数民族学生参与研究和实践以及参与为 K-12 学生定制的推广项目来改善智能系统设计的知识库。此外，该项目将倡导基于网络的界面和研讨会来传播最新的研究成果。微处理器已成为我们现代生活中无处不在且至关重要的一部分。然而，他们在人工智能系统中面临着严峻的问题，需要大量的能量和数据来训练和运行复杂的算法。相反，各种大小的动物大脑在学习和准确性方面取得了非凡的成就，而能源成本远低于人类工程系统。因此，该项目的中心主题是将大脑结构和功能的最新知识转移到神经拟态设计中，为改进工程系统产生新的见解，并在严格的精度限制下实现高精度和高能效。纳米级组件。这些神经生物学原理包括低精度突触的近似学习规则、兴奋和抑制的神经基序以及分层网络模型。其目标是用更少的数据量和资源完成复杂的计算，并有望比当今的微处理器大幅提高能源效率和性能。

项目成果

Towards efficient neural networks on-a-chip: Joint hardware-algorithm approaches

迈向高效的片上神经网络：联合硬件算法方法

• 发表时间: 2019
• 期刊: China Semiconductor Technology International Conference
• 作者: Du, X.;Krishnan, G.;Mohanty, A.;Li, Z.;Charan, G.;Cao, Y.
• 通讯作者: Cao, Y.

Automatic Compilation of Diverse CNNs Onto High-Performance FPGA Accelerators

• DOI: 10.1109/tcad.2018.2884972
• 发表时间: 2020-02-01
• 期刊: IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
• 影响因子: 2.9
• 作者: Ma, Yufei;Cao, Yu;Seo, Jae-sun
• 通讯作者: Seo, Jae-sun

Efficient Network Construction Through Structural Plasticity

• DOI: 10.1109/jetcas.2019.2933233
• 发表时间: 2019-05
• 期刊: IEEE Journal on Emerging and Selected Topics in Circuits and Systems
• 影响因子: 4.6
• 作者: Xiaocong Du;Zheng Li;Yufei Ma;Yu Cao

Accurate Inference With Inaccurate RRAM Devices: A Joint Algorithm-Design Solution

使用不准确的 RRAM 器件进行准确推理：联合算法设计解决方案

• DOI: 10.1109/jxcdc.2020.2987605
• 发表时间: 2020
• 期刊: IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
• 影响因子: 2.4
• 作者: Charan, Gouranga;Mohanty, Abinash;Du, Xiaocong;Krishnan, Gokul;Joshi, Rajiv V.;Cao, Yu
• 通讯作者: Cao, Yu

Structured Pruning of RRAM Crossbars for Efficient In-Memory Computing Acceleration of Deep Neural Networks

• DOI: 10.1109/tcsii.2021.3069011
• 发表时间: 2021-05
• 期刊: IEEE Transactions on Circuits and Systems II: Express Briefs
• 作者: Jian Meng;Li Yang;Xiaochen Peng;Shimeng Yu;Deliang Fan;Jae-sun Seo