Leaky Integrate and Fire Neuron by Charge-Discharge Dynamics in Floating-Body MOSFET.

Leaky Integrate and Fire Neuron by Charge-Discharge Dynamics in Floating-Body MOSFET.
复制标题

DOI:
10.1038/s41598-017-07418-y
复制
发表时间:
2017-08-15
期刊:
影响因子:
4.6
通讯作者:
Ganguly U
Ganguly U
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Dutta S;Kumar V;Shukla A;Mohapatra NR;Ganguly U

文献摘要

参考文献

被引文献

相似文献

神经生物学启发的尖峰神经网络(SNN)可以实现高效的学习和识别任务。为了实现类似于生物学的大规模网络,功率和面积高效的电子神经元是必不可少的。在此之前,我们已经通过物理模拟展示了一种新型的基于n+/p/n+的四端碰撞电离的LIF神经元,该器件具有扩展的栅极(gated-INPN)器件。与传统的模拟电路实现相比,观察到在面积和功率方面的出色改进。在本文中,我们提出并实验证明了一个紧凑的传统的3端部分耗尽(PD)SOI- MOSFET(100 nm的栅极长度),以取代4端栅INPN器件。利用SOI-MOSFET中的碰撞电离(II)引起的浮体效应来捕获LIF神经元的行为,以证明尖峰频率对输入的依赖性。MHz操作实现了与生物学相比有吸引力的硬件加速。总的来说,传统的PD-SOI-CMOS技术实现了超大规模集成(VLSI),这对于生物规模(~1011个基于神经元的)大型神经网络是必不可少的。
Neuro-biology inspired Spiking Neural Network (SNN) enables efficient learning and recognition tasks. To achieve a large scale network akin to biology, a power and area efficient electronic neuron is essential. Earlier, we had demonstrated an LIF neuron by a novel 4-terminal impact ionization based n+/p/n+ with an extended gate (gated-INPN) device by physics simulation. Excellent improvement in area and power compared to conventional analog circuit implementations was observed. In this paper, we propose and experimentally demonstrate a compact conventional 3-terminal partially depleted (PD) SOI- MOSFET (100 nm gate length) to replace the 4-terminal gated-INPN device. Impact ionization (II) induced floating body effect in SOI-MOSFET is used to capture LIF neuron behavior to demonstrate spiking frequency dependence on input. MHz operation enables attractive hardware acceleration compared to biology. Overall, conventional PD-SOI-CMOS technology enables very-large-scale-integration (VLSI) which is essential for biology scale (~1011 neuron based) large neural networks.
DOI: 10.1109/tnn.2005.860850
发表时间: 2006-01-01
影响因子: --
作者:
Indiveri, G;Chicca, E;Douglas, R
通讯作者: Douglas, R
DOI: 10.1109/tnn.2003.820440
发表时间: 2003-11-01
影响因子: --
作者:
Izhikevich, EM
通讯作者: Izhikevich, EM
DOI: 10.1038/nnano.2016.70
发表时间: 2016-08-01
影响因子: 38.3
作者:
Tuma, Tomas;Pantazi, Angeliki;Eleftheriou, Evangelos
通讯作者: Eleftheriou, Evangelos
DOI: 10.1016/j.neunet.2007.12.037
发表时间: 2008-03-01
期刊: NEURAL NETWORKS
影响因子: 7.8
作者:
Wijekoon, Jayawan H. B.;Dudek, Piotr
通讯作者: Dudek, Piotr
DOI: 10.1016/j.neucom.2012.01.042
发表时间: 2013-02-15
期刊: NEUROCOMPUTING
影响因子: 6
作者:
Basu, Arindam;Shuo, Sun;Huang, Guang-Bin
通讯作者: Huang, Guang-Bin