A Stochastic Leaky-Integrate-and-Fire Neuron Model With Floating Gate-Based Technology for Fast and Accurate Population Coding
A Stochastic Leaky-Integrate-and-Fire Neuron Model With Floating Gate-Based Technology for Fast and Accurate Population Coding
复制标题
采用基于浮栅技术的随机泄漏积分激发神经元模型，可实现快速准确的群体编码
DOI：
10.1109/jeds.2022.3206317
复制
发表时间：
2022
影响因子：
2.3
通讯作者：
Chihiro Matsui and Ken Takeuchi
中科院分区：
文献类型：
--
作者：
Akira Goda;Chihiro Matsui and Ken Takeuchi
提出了一种基于浮栅技术的随机漏积分激发神经元的解析模型。对于单个神经元和神经元群体的随机行为已经进行了广泛的建模。在FG LIF神经元中，电子注入由通过栅极氧化物的隧穿过程控制，导致注入时间和尖峰间期（ISI）随机性的指数分布。通过模拟FG LIF神经元群体的随机行为，证明了群体编码的概念。ISI随机性使得能够将输入信号编码为总体输出。尖峰到尖峰的随机性提高了总体输出的信噪比。此外，ISI分布的形状可以通过调整要尖峰的电子的数量（内斯）来控制。通过减小内斯，实现了指数型ISI分布。随着指数样ISI分布，快速发放神经元的数量显著增加（超过10%的神经元发放速度比平均ISI快两倍），这可能有助于快速计算。最后，已经提出了逐步过程来设计表现出期望的神经元特性的FG LIF神经元，所述期望的神经元特性包括操作电压（0.5V至3V）、泄漏时间常数（>10 ms）、ISI平均值（在6个数量级的范围内）和随机性（~ 0%至~ 60%）以及分布的类型（类指数至类高斯）。
An analytical model has been developed for stochastic leaky-integrate-and-fire (LIF) neurons with floating gate (FG) technology. The stochastic behaviors have been modeled extensively for both individual neurons and populations of neurons. In the FG LIF neurons, the electron injection is governed by the tunneling process through the gate oxide, leading to the exponential distributions of the injection time and inter spike interval (ISI) stochasticity. The concept of the population coding is demonstrated by simulating the stochastic behaviors of the populations of the FG LIF neurons. The ISI stochasticity enables encoding of the input signals to the population outputs. Spike-to-spike stochasticity improves the signal-to-noise ratio of the population outputs. Moreover, the shape of the ISI distribution can be controlled by adjusting the number of electrons to spike (NES). Exponential-like ISI distributions are realized by reducing the NES. With the exponential-like ISI distributions, the population of fast spiking neurons increases significantly (more than 10% of neurons spiking twice faster than the mean ISI), potentially contributing to the fast computation. Finally, step-by-step procedures have been proposed to design the FG LIF neurons exhibiting the desired neuron characteristics including operation voltage (0.5 V to 3 V), leaky time constantto >10 ms), ISI mean (in the range of 6 orders of magnitude) and stochasticity ~0 % to ~60 %) as well as the type of the distribution (exponential-like to Gaussian-like).
登录
查看更多内容
影响因子：
3.1
作者：
Auge, Daniel;Hille, Julian;Knoll, Alois
通讯作者：
Knoll, Alois
用于尖峰神经网络硬件的基于浮栅技术的神经元的尖峰间隔和随机性工程
DOI：
--
发表时间：
2022
期刊：
影响因子：
--
作者：
Akira Goda;Chihiro Matsui and Ken Takeuchi
通讯作者：
Chihiro Matsui and Ken Takeuchi
影响因子：
3.1
作者：
Brigner, Wesley H.;Friedman, Joseph S.;Garcia-Sanchez, Felipe
通讯作者：
Garcia-Sanchez, Felipe
影响因子：
38.3
作者：
Tuma, Tomas;Pantazi, Angeliki;Eleftheriou, Evangelos
通讯作者：
Eleftheriou, Evangelos
少电子现象对浮栅存储器可靠性的影响
DOI：
10.1109/iedm.2004.1419320
发表时间：
2004
期刊：
IEDM Technical Digest. IEEE International Electron Devices Meeting, 2004.
影响因子：
--
作者：
Gabriel Molas;D. Deleruyelle;B. D. Salvo;Gérard Ghibaudo;M. Gely;S. Jacob;D. Lafond;S. Deleonibus
通讯作者：
S. Deleonibus