Neuromorphic computing with non-volatile memory (NVM) can significantly improve performance and lower energy consumption of machine learning tasks implemented using spike-based computations and bio-inspired learning algorithms. High voltages required to operate certain NVMs such as phase-change memory (PCM) can accelerate aging in a neuron's CMOS circuit, thereby reducing the lifetime of neuromorphic hardware. In this work, we evaluate the long-term, i.e., lifetime reliability impact of executing state-of-the-art machine learning tasks on a neuromorphic hardware, considering failure models such as negative bias temperature instability (NBTI) and time-dependent dielectric breakdown (TDDB). Based on such formulation, we show the reliability-performance trade-off obtained due to periodic relaxation of neuromorphic circuits, i.e., a stop-and-go style of neuromorphic computing.
Energy-Efficient Neuromorphic Computing for Edge AI: A Framework with Adaptive Spiking Neural Networks and Hardware-Aware Optimization
Department of Applied Mathematics and Computer Science (DTU Compute)(应用数学与计算机科学系(DTU计算));Department of Engineering(工程系);Department of Computer Engineering(计算机工程系);Department of Mathematics(数学系);Department of Computer Systems(计算机系统系)
Energy-Aware Spike Budgeting for Continual Learning in Spiking Neural Networks for Neuromorphic Vision
Dept. of Electrical and Electronics Engineering, University of Liberal Arts Bangladesh(乌拉尔大学 bangladesh 电子与电气工程系);Dept. of Electrical Engineering, Pennsylvania State University(宾夕法尼亚州立大学电气工程系)
NeuroNAS: Enhancing Efficiency of Neuromorphic In-Memory Computing for Intelligent Mobile Agents through Hardware-Aware Spiking Neural Architecture Search
Thermal-Aware Compilation of Spiking Neural Networks to Neuromorphic Hardware
类脑计算的硬件实现可以显著提高用脉冲神经网络(SNN)实现的机器学习任务的性能和能量效率,使得这些硬件平台特别适合于嵌入式系统和其他能量受限的环境。我们观察到,当通过其突触元件传播尖峰时,硬件的交叉开关中的长位线和字线产生显著的电流变化,突触元件通常设计有非易失性存储器(NVM)。这样的电流变化在硬件的每个交叉杆内创建热梯度,这取决于机器学习工作负载以及工作负载的神经元和突触到这些交叉杆的映射。\mr{This thermal gradient becomes significant at scaled technology nodes and it increases the leakage power in the hardware leading to an increase in the energy consumption.}我们提出了一种新的技术,将基于SNN的机器学习工作负载的神经元和突触映射到神经形态硬件。我们做了两个新的贡献。首先,我们制定了一个详细的热模型的神经形态硬件中的交叉杆纳入工作负载的依赖性,其中每个基于NVM的突触细胞的温度计算考虑其相邻细胞的热贡献。其次,我们将这个热模型的映射神经元和突触的SNN为基础的工作负载使用爬山启发式。其目的是减少交叉杆中的热梯度。我们使用最先进的神经形态硬件的10个机器学习工作负载来评估我们的神经元和突触映射技术。我们证明…
Neuromorphic Energy-Aware Learning for Adaptive Deep Brain Stimulation
Dept. of Electrical and Computer Engineering, University of California, Santa Cruz, CA, USA(加州大学圣克鲁兹分校电气与计算机工程系);Dept. of Bioengineering, University of California, San Diego, La Jolla, CA, USA(加州大学圣地亚哥分校生物工程系)
Hardware-aware training of models with synaptic delays for digital event-driven neuromorphic processors
Instituto de Microelectrónica de Sevilla, CSIC/Universidad de Sevilla(塞维利亚微电子研究所,西班牙国家研究委员会/塞维利亚大学);Eindhoven University of Technology(埃因霍温理工大学);IMEC-Netherlands(比利时微电子研究中心荷兰分部);University of Twente(特温特大学)
A feedback control optimizer for online and hardware-aware training of Spiking Neural Networks
Institute of Neuroinformatics, University of Zürich and ETH Zürich(神经信息学研究所,苏黎世大学和苏黎世联邦理工学院);ETH Zürich, Zürich, Switzerland(苏黎世联邦理工学院,苏黎世,瑞士);Digital Society Initiative, University of Zurich, Switzerland(数字社会倡议,苏黎世大学,瑞士);AI Center, ETH, Zürich, Switzerland(人工智能中心,苏黎世联邦理工学院,苏黎世,瑞士)
A Neuromorphic VLSI Design for Spike Timing and Rate Based Synaptic Plasticity
基于三联体的尖峰时间依赖可塑性(TSTDP)是一种强大的突触可塑性规则,其作用超出了传统的基于对的STDP(PSTDP)。在这里,TSTDP能够再现各种生物实验的结果,而PSTDP规则无法再现它们。此外,它已被证明,固有的行为,以尖峰率为基础的Bienenstock-Cooper-Munro(B-M)突触可塑性规则也可以出现从TSTDP规则。本文提出了一种模拟实现的TSTDP规则。建议的超大规模集成电路设计使用AMS 0.35 μ m CMOS工艺,并已使用Synopsys和Cadence工具的设计套件进行了模拟。仿真结果表明,如何以及所提出的电路可以改变突触的权重,根据一组不同的尖峰模式之间的定时差。此外,该电路被示出产生一个类似于BCM的学习规则,这是一个基于速率的规则。为了模拟实现环境,对所提出的电路进行了1000次运行的蒙特卡罗(MC)分析。所提出的MC仿真分析和微调电路的仿真结果表明,这是可能的,以减轻工艺变化的影响,在概念验证电路,然而,一个实际的变化意识的设计技术,需要保证高的电路性能在大规模神经网络。我们相信,所提出的设计可以发挥重要作用,在未来的超大规模集成电路实现的尖峰定时和基于速率的神经形态学习系统。
Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Shenzhen Research Institute of Big Data(深圳大数据研究院);School of Public Health, Peking University(北京大学公共卫生学院);Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院);Peng Cheng Laboratory(鹏城实验室)