期刊
FRONTIERS IN NEUROSCIENCE
卷 15, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fnins.2021.655823
关键词
phase transition materials; VO2; nano-oscillators; ONNs; neuromorphics
资金
- NeurONN Project (Horizon 2020) [871501]
- Ministerio de Economia y Competitividad del Gobierno de Espana
- FEDER [TEC2017-87052-P]
- CSIC Open Access Publication Support Initiative through its Unit of Information Resources for Research (URICI)
A new architecture for ONNs based on VO2 devices is proposed in this study, using SHIL to ensure each neuron's phase information can only take two values. Compared to conventional interconnection schemes, this architecture offers better robustness and tolerance.
Nano-oscillators based on phase-transition materials are being explored for the implementation of different non-conventional computing paradigms. In particular, vanadium dioxide (VO2) devices are used to design autonomous non-linear oscillators from which oscillatory neural networks (ONNs) can be developed. In this work, we propose a new architecture for ONNs in which sub-harmonic injection locking (SHIL) is exploited to ensure that the phase information encoded in each neuron can only take two values. In this sense, the implementation of ONNs from neurons that inherently encode information with two-phase values has advantages in terms of robustness and tolerance to variability present in VO2 devices. Unlike conventional interconnection schemes, in which the sign of the weights is coded in the value of the resistances, in our proposal the negative (positive) weights are coded using static inverting (non-inverting) logic at the output of the oscillator. The operation of the proposed architecture is shown for pattern recognition applications.
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