Neuromorphic computing with multi-memristive synapses.

Neuromorphic computing with multi-memristive synapses.
复制标题

DOI:
10.1038/s41467-018-04933-y
复制
发表时间:
2018-06-28
影响因子:
16.6
通讯作者:
Eleftheriou E
Eleftheriou E
中科院分区:
综合性期刊1区
文献类型:
--
作者:
Boybat I;Le Gallo M;Nandakumar SR;Moraitis T;Parnell T;Tuma T;Rajendran B;Leblebici Y;Sebastian A;Eleftheriou E

文献摘要

参考文献

被引文献

相似文献

神经形态计算已成为构建下一代智能计算系统的一条有前途的途径。有人提出,忆阻装置表现出依赖于历史的电导率调制,可以有效地表示人工神经网络中的突触权重。然而,在宽动态范围内对器件电导进行精确调制(维持高网络精度所必需的)被证明具有挑战性。为了解决这个问题,我们提出了一种具有高效全局计数器仲裁方案的多重忆阻突触架构。我们专注于相变存储器件,开发了一个综合模型,并通过模拟证明了该概念对于尖峰和非尖峰神经网络的有效性。此外,我们还展示了涉及超过一百万个相变存储设备的实验结果,用于使用尖峰神经网络进行时间相关性的无监督学习。这项工作向实现大规模、节能的神经形态计算系统迈出了重要一步。忆阻技术是实现高效非冯诺依曼神经形态硬件的一条有前途的途径。博伊巴特等人。提出了一种具有基于计数器的全局仲裁方案的多忆阻突触架构,以解决与非理想忆阻设备行为相关的挑战。
Neuromorphic computing has emerged as a promising avenue towards building the next generation of intelligent computing systems. It has been proposed that memristive devices, which exhibit history-dependent conductivity modulation, could efficiently represent the synaptic weights in artificial neural networks. However, precise modulation of the device conductance over a wide dynamic range, necessary to maintain high network accuracy, is proving to be challenging. To address this, we present a multi-memristive synaptic architecture with an efficient global counter-based arbitration scheme. We focus on phase change memory devices, develop a comprehensive model and demonstrate via simulations the effectiveness of the concept for both spiking and non-spiking neural networks. Moreover, we present experimental results involving over a million phase change memory devices for unsupervised learning of temporal correlations using a spiking neural network. The work presents a significant step towards the realization of large-scale and energy-efficient neuromorphic computing systems. Memristive technology is a promising avenue towards realizing efficient non-von Neumann neuromorphic hardware. Boybat et al. proposes a multi-memristive synaptic architecture with a counter-based global arbitration scheme to address challenges associated with the non-ideal memristive device behavior.
DOI: 10.1038/ncomms14736
发表时间: 2017-04-03
影响因子: 16.6
作者:
Boyn S;Grollier J;Lecerf G;Xu B;Locatelli N;Fusil S;Girod S;Carrétéro C;Garcia K;Xavier S;Tomas J;Bellaiche L;Bibes M;Barthélémy A;Saïghi S;Garcia V
通讯作者: Garcia V
使用电阻交叉点设备的深度神经网络训练的加速:设计注意事项。
DOI: 10.3389/fnins.2016.00333
发表时间: 2016
影响因子: 4.3
作者:
Gokmen T;Vlasov Y
通讯作者: Vlasov Y
DOI: 10.1007/s00339-011-6264-9
发表时间: 2011-03-01
影响因子: 2.7
作者:
Chua, Leon
通讯作者: Chua, Leon
DOI: 10.1109/ted.2015.2439635
发表时间: 2015-11-01
影响因子: 3.1
作者:
Burr, Geoffrey W.;Shelby, Robert M.;Hwang, Hyunsang
通讯作者: Hwang, Hyunsang
DOI: 10.1038/31709
发表时间: 1998-06-25
期刊: NATURE
影响因子: 64.8
作者:
Benke, TA;Lüthi, A;Collingridge, GL
通讯作者: Collingridge, GL