Yan Yu and Wang Yu and Chen Xintong and Liu Yi and Zhang Yanzhong and Wang Yanji and Chen Xingyu and Zhang Miaocheng and Tong Yi
Artificial Neurons Based on Memristors for Spiking Neural Networks
437 - 440
2022
16
10
International Journal of Electronics and Communication Engineering
https://publications.waset.org/pdf/10012716
https://publications.waset.org/vol/190
World Academy of Science, Engineering and Technology
Neuromorphic computing based on spiking neural networks (SNNs) has emerged as a promising avenue for building the next generation of intelligent computing systems. Owing to their highdensity integration, low power, and outstanding nonlinearity, memristors have attracted emerging attention on achieving SNNs. However, fabricating a lowpower and robust memristorbased spiking neuron without extra electrical components is still a challenge for braininspired systems. In this work, we demonstrate a TiO2based threshold switching (TS) memristor to emulate a leaky integrateandfire (LIF) neuron without auxiliary circuits, used to realize single layer fully connected (FC) SNNs. Moreover, our TiO2based resistive switching (RS) memristors realize spikingtimedependentplasticity (STDP), originating from the Ag diffusionbased filamentary mechanism. This work demonstrates that TiO2based memristors may provide an efficient method to construct hardware neuromorphic computing systems.
Open Science Index 190, 2022