期刊
IEEE TRANSACTIONS ON ELECTRON DEVICES
卷 69, 期 5, 页码 2368-2376出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TED.2022.3160140
关键词
Biological neuron; numerical modeling; spiking neural networks; stochastic firing
资金
- Project Optimization of Vacuum Thin Film and Nanoparticle Technologies - Operational Program Competitiveness, Entrepreneurship and Innovation (NSRF 2014-2020) [MIS5002772]
- European Union (European Regional Development Fund)
- Project Optimization of Vacuum Thin Film and Nanoparticle Technologies - Operational Program Competitiveness, Entrepreneurship and Innovation (National Strategic Reference Framework (NSRF) 2014-2020) [MIS5002772]
- Hellenic Foundation for Research and Innovation (HFRI) through the First Call for HFRI Research Projects to support Faculty Members and Researchers and the Procurement of High-Cost Research Equipment Grant [3830]
A 2-D dynamical model is proposed to explain the memristive properties in a bilayer structure and investigate the influence of a dense layer of Pt nanoparticles on thermal distribution. By simulating probabilistic leaky-integrate-and-fire neuron properties, Bayesian extrapolation is achieved in a spiking neural network. The classification application using a liver tumor dataset highlights the advantages of stochastic-based spike neural networks in terms of accuracy and power consumption compared to conventional artificial neural networks and deterministic-based spike neural networks.
A deep understanding of the underlying resistive switching mechanism for the implementation of volatile memristive properties is regarded as of great importance for enhancing their performance. Along these lines, a 2-D dynamical model is introduced to interpret the whole memristive pattern within the bilayer configuration, as well as the crucial of the dense layer of the Pt nanoparticles (NPs) on the local thermal distribution. Moreover, the probabilistic leaky-integrate-and-fire (LIF) neuron properties were simulated by considering a simple RC circuit in order to perform Bayesian extrapolation within a spiking neural network. A classification application is consequently demonstrated by using the liver tumor dataset. The advantageous capabilities of the stochastic-based spike neural networks (SNNs) are highlighted in striking contrast with the conventional artificial neural networks (ANNs), as well as the deterministic-based SNNs, in terms of prediction accuracy and power consumption.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据