Search

Due to their high similarity to biological ion channels, low power consumption, small footprint, and the fact that they do not require reset circuits, threshold switching memristors have been intensively studied for simulating neurons in neuromorphic chips. Switching speed is one of the key challenges which limit the application of threshold switching memristors in chips. In this study, Ta2O5 threshold switching memristors with high switching speeds were prepared by doping with silver. The results show that 14 wt. % Ag doped Ta2O5 threshold switching memristors exhibit excellent bi-directional threshold switching performance, featuring fast switching speeds (<20 ns, <18 ns), low leakage currents (<10 pA), and high switching ratio (>107). According to the field nucleation theory, the rapid switching speed can be attributed to the low nucleation energy (0.26 eV) of silver within the Ta2O5 matrix, which is achieved by incorporating 14 wt. % Ag during the doping process. Based on Pspice, a LIF (leaky integrate-and-fire) neuron based on the silver nanoparticles doped Ta2O5 threshold switching memristors is built, and its firing function has been simulated. The results show that the LIF neuron with a short switching time is able to excite pulse spiking with high frequencies. These results demonstrated that the silver nanoparticles doped Ta2O5-based threshold switching memristors hold significant potential for constructing high-speed artificial neural networks. [ABSTRACT FROM AUTHOR]

The flexible memristor synapses based on binary metal oxides have significant potential in building artificial neural networks to meet people's demands. To obtain flexible memristor synapses with high linearity of conductance update, herein, the effect of Al doping and SiOx layer adding on the flexible TiOx‐based memristor synapse even under bending is studied. The results show that the doping Al and adding SiOx layer improves the linearity of conductance update by 3 times. The bending test results of the SiOx/Al:TiOx‐based memristor synapse show that the linearity decreases slightly with the decrease of the bending radius. When the bending radius is reduced to 5 mm, the total nonlinearity (NL) value of the device is about 0.42. It is still much smaller than the total NL value of TiOx‐based memristor synapse in flat state (about 0.76). The test results of conducting atomic force microscopy show that the improvement of linearity is due to the optimization of conductive filaments. The results provide a feasible program for improving linearity of TiOx‐based flexible memristor synapse even under bending, which can support for the development of high‐performance binary metal oxide flexible memristor synapse. [ABSTRACT FROM AUTHOR]

Hafnium oxide (HfOx) memristor has attracted enormous attention due to its high performance and back-end-of-line (BEOL) compatibility, thus providing a novel approach to implementing artificial intelligence neural networks. In this work, great performance optimization of HfOx memristor has been achieved by using atomic layer deposition (ALD) method and post-metal annealing (PMA) process, in which both procedures are with low-temperature budget (< 300 °C) and are compatible with CMOS BEOL process. The device exhibits forming-free, high yield, good linearity, fast speed and non-volatile characteristics. Besides, the device conductance can be well modulated by using the most desired pulse protocol, namely the identical pulse with same pulse amplitude and width. More than 3bit stable conductance states have been obtained, indicating its great potential in practical memristor neuromorphic computing system. [ABSTRACT FROM AUTHOR]

Neuromorphic computing has the potential to accelerate high performance parallel and low power in-memory computation, artificial intelligence, and adaptive learning. Despite emulating the basic functions of biological synapses well, the existing artificial electronic synaptic devices have yet to match the softness, robustness, and ultralow power consumption of the brain. Here, we demonstrate an all-inorganic flexible artificial synapse enabled by a ferroelectric field effect transistor based on mica. The device not only exhibits excellent electrical pulse modulated conductance updating for synaptic functions but also shows remarkable mechanical flexibility and high temperature reliability, making robust neuromorphic computation possible under external disturbances such as stress and heating. Based on its linear, repeatable, and stable long-term plasticity, we simulate an artificial neural network for the Modified National Institute of Standards and Technology handwritten digit recognition with an accuracy of 94.4%. This work provides a promising way to enable flexible, low-power, robust, and highly efficient neuromorphic computation that mimics the brain. [ABSTRACT FROM AUTHOR]