E2CDA: Type II: Self-Adaptive Reservoir Computing with Spiking Neurons: Learning Algorithms and Processor Architectures

E2CDA：类型 II：带尖峰神经元的自适应储层计算：学习算法和处理器架构

• 批准号: 1940761
• 负责人: Peng Li
• 金额: $ 21.57万
• 依托单位: University of California-Santa Barbara
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-07-01 至 2020-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1940761&HistoricalAwards=false
• 关键词: E2CDA; Type; II; Self; Adaptive

While computing has become increasingly data centric across many disciplines, conventional computer architectures have limited potential in meeting the escalating performance and energy efficiency needs in this era of data-driven science and engineering. This project aims to develop brain-inspired neural models of computation and adaptive processor architectures to enable intelligent data processing and learning in a wide range of applications. While being strongly interdisciplinary, this work will bridge neuroscience, artificial neural networks, computer architecture, and hardware engineering. The planned research will provide rich training and educational opportunities to students, and produce new curriculum. Research participation from undergraduate and underrepresented students will be promoted. The outcomes of this project will be broadly disseminated. Research collaboration with the US industry will be actively pursued via interaction with the Semiconductor Research Corporation. This work is aimed at attaining brain-like learning performance by imitating how the brain represents, processes, and learns from information, and more specifically, by developing models of computation based on the third-generation spiking neural networks, and efficient adaptive processor architectures. Within the framework of so called reservoir computing, the proposed neural models mimic key characteristics of the brain such as information processing based on spike timing. Furthermore, this project will develop brain-inspired learning mechanisms to allow training of complex recurrent spiking neural networks. Self-adaptive processor architectures with integrated on-chip learning, light-weight runtime learning performance prediction, and energy management will be developed to maximize system energy efficiency while providing a guarantee of performance.

尽管计算在许多学科中越来越以数据为中心，但传统的计算机架构在满足数据驱动的科学和工程时代的效果和能源效率需求方面的潜力有限。该项目旨在开发以脑为脑启发的计算和自适应处理器体系结构的神经模型，以在广泛的应用中实现智能数据处理和学习。在强烈的跨学科的同时，这项工作将弥合神经科学，人工神经网络，计算机架构和硬件工程。计划的研究将为学生提供丰富的培训和教育机会，并提供新的课程。本科生和代表性不足的学生的研究参与将得到促进。该项目的结果将被广泛传播。与美国行业的研究合作将通过与半导体研究公司的互动来积极追求。这项工作旨在通过模仿大脑如何代表，过程和从信息中学习，更具体地说，是通过基于第三代尖峰神经网络以及有效的适应性处理器体系结构来开发计算模型，从而获得类似大脑的学习表现。 在所谓的储层计算的框架内，提出的神经模型模仿大脑的关键特征，例如基于峰值时间的信息处理。此外，该项目将开发出脑启发的学习机制，以允许训练复杂的复发性尖峰神经网络。具有集成的片上学习，轻量级运行时学习绩效预测和能量管理的自适应处理器体系结构将开发出最大化的系统能效，同时提供性能的保证。

项目成果

Enabling Non-Hebbian Learning in Recurrent Spiking Neural Processors With Hardware-Friendly On-Chip Intrinsic Plasticity

• DOI: 10.1109/jetcas.2019.2934939
• 发表时间: 2019-08
• 期刊: IEEE Journal on Emerging and Selected Topics in Circuits and Systems
• 影响因子: 4.6
• 作者: Yu Liu;Wenrui Zhang;Peng Li

Information-Theoretic Intrinsic Plasticity for Online Unsupervised Learning in Spiking Neural Networks

• DOI: 10.3389/fnins.2019.00031
• 发表时间: 2019-02
• 期刊: Frontiers in Neuroscience
• 影响因子: 4.3
• 作者: Wenrui Zhang;Peng Li

Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks

• 发表时间: 2019-08
• 作者: Wenrui Zhang;Peng Li

Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks

• DOI: 10.48550/arxiv.1805.07866
• 发表时间: 2018-01-01
• 期刊: P ADV NEUR INF PROC
• 作者: Jin, Y.;Zhang, W.;Li, P.
• 通讯作者: Li, P.

Spike-Train Level Direct Feedback Alignment: Sidestepping Backpropagation for On-Chip Training of Spiking Neural Nets

• DOI: 10.3389/fnins.2020.00143
• 发表时间: 2020-03-13
• 期刊: FRONTIERS IN NEUROSCIENCE
• 影响因子: 4.3
• 作者: Lee, Jeongjun;Zhang, Renqian;Li, Peng
• 通讯作者: Li, Peng